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

    Neuronpedia

    INDEX
    Explanations

    baking, soda, colleges, voice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rivial
    0.49
    :
    0.49
     for
    0.48
    uv
    0.42
     process
    0.42
     uv
    0.42
    rm
    0.41
     moment
    0.41
    uris
    0.41
     quantify
    0.41
    POSITIVE LOGITS
    たつ
    0.50
    たくさんの
    0.49
    大な
    0.49
    句話
    0.48
    フォロー
    0.47
    टेट
    0.46
     ويل
    0.45
    anía
    0.44
    ثمان
    0.44
     Thib
    0.44
    Act Density 0.001%

    No Known Activations