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

    Neuronpedia

    INDEX
    Explanations

    references to funding sources and acknowledgments in research documents

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

    section headers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    transQ
    -0.66
     snippetHide
    -0.54
    featureID
    -0.54
     kasarigan
    -0.47
    IntoConstraints
    -0.47
     aDecoder
    -0.45
     TextInputType
    -0.45
    ----</
    -0.44
    StringCopy
    -0.44
     ligiloj
    -0.44
    POSITIVE LOGITS
    ]")]
    0.48
    EndInit
    0.48
    awtextra
    0.47
     grind
    0.41
    morgen
    0.40
     Addis
    0.40
    iddhar
    0.40
    isierten
    0.39
    けると
    0.39
    tan
    0.39
    Act Density 0.016%

    No Known Activations