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

    Neuronpedia

    INDEX
    Explanations

    words/phrases that indicate a sequence of steps

    oai_token-act-pair · gemini-2.0-flash

    sequencing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.59
    StructEnd
    -0.58
    ToFit
    -0.54
    ิลป
    -0.49
    ://"
    -0.48
     piaci
    -0.47
     اطلع
    -0.47
     gră
    -0.46
     FAB
    -0.46
     millón
    -0.45
    POSITIVE LOGITS
    出版年
    0.66
    onesi
    0.60
    expandindo
    0.59
     समीक्षाओं
    0.57
    tadır
    0.56
    principalTable
    0.55
    ゴリー
    0.55
     noDo
    0.55
     الحره
    0.53
    perma
    0.52
    Act Density 0.336%

    No Known Activations