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

    Neuronpedia

    INDEX
    Explanations

    word, phrase, or adjective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     revolt
    0.48
    "]:
    0.48
     or
    0.47
     входят
    0.46
     those
    0.45
     umana
    0.44
     происхождения
    0.44
     raggiungere
    0.44
     pengalaman
    0.43
     in
    0.43
    POSITIVE LOGITS
    ált
    0.54
    ያስ
    0.52
    يمي
    0.49
    AY
    0.47
    ursing
    0.47
    zech
    0.46
    cheduler
    0.46
     Butterworth
    0.46
    ニュー
    0.46
    MIER
    0.46
    Act Density 0.000%

    No Known Activations