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

    Neuronpedia

    INDEX
    Explanations

    pronouns and verb words related to people

    oai_token-act-pair · gemini-2.0-flash

    Instructions or advice

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dry
    -0.63
    addImage
    -0.55
    dry
    -0.54
    illiard
    -0.54
     Dry
    -0.53
     Pair
    -0.52
     Pairs
    -0.50
    sproz
    -0.50
     teaching
    -0.49
    Dry
    -0.49
    POSITIVE LOGITS
    jspx
    0.70
     BorderRadius
    0.70
    ConstraintMaker
    0.62
    elemField
    0.60
    BeginInit
    0.60
     समीक्षक
    0.59
    endpush
    0.59
     dig
    0.58
    endphp
    0.58
    MemoryWarning
    0.57
    Act Density 5.329%

    No Known Activations