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

    Neuronpedia

    INDEX
    Explanations

    the word "all"

    oai_token-act-pair · gemini-2.0-flash

    all

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -1.05
     all
    -0.60
    All
    -0.54
     All
    -0.52
    all
    -0.48
     ALL
    -0.46
     producing
    -0.45
    ">{{$
    -0.44
    所有的
    -0.44
    __':
    -0.42
    POSITIVE LOGITS
     nahilalakip
    0.98
    tvguidetime
    0.83
    parsedMessage
    0.79
    RetentionPolicy
    0.76
    AnimationsModule
    0.74
    MethodManager
    0.73
     handleMessage
    0.73
    rrggbb
    0.72
    NewLabel
    0.72
    setVerticalGroup
    0.70
    Act Density 0.237%

    No Known Activations