Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to study design and implications of research findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    like "implications," "limitations," or "discussion."

    np_acts-logits-general · gemini-2.0-flash

    discussion of implications and limitations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Біографія
    -0.51
    __(/*!
    -0.47
    majánló
    -0.45
    sizeCache
    -0.45
    Datuak
    -0.44
     dyn
    -0.44
    happily
    -0.44
     "..\..\
    -0.43
     stripes
    -0.43
    ThroughAttribute
    -0.42
    POSITIVE LOGITS
     implications
    0.59
     Implications
    0.44
     conclusions
    0.43
    SourceChecksum
    0.41
    Implications
    0.40
    ThemeOverlay
    0.39
     conclusion
    0.39
    AnchorTagHelper
    0.39
    ayangkan
    0.37
    UrlResolution
    0.37
    Act Density 1.178%

    No Known Activations