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

    Neuronpedia

    INDEX
    Explanations

    formal documents and references to official meetings or reports

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

    Followed by numbers or punctuation

    np_acts-logits-general · gemini-2.0-flash

    formal documents and discussions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Diweddarwch
    -0.35
     univers
    -0.32
     benz
    -0.31
    }}],
    -0.30
    TF
    -0.30
     tür
    -0.30
    makeText
    -0.29
    RunWith
    -0.29
    TN
    -0.28
     jamás
    -0.28
    POSITIVE LOGITS
    verwijspagina
    0.67
    yntaxException
    0.60
    DockStyle
    0.60
     voted
    0.58
    WebVitals
    0.58
    ModelAdmin
    0.57
     transfieras
    0.56
    ErrUnexpectedEOF
    0.56
    InputBorder
    0.56
    AndEndTag
    0.55
    Act Density 0.076%

    No Known Activations