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

    Neuronpedia

    INDEX
    Explanations

    showing or demonstration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ם
    0.82
    س
    0.77
     ORGAN
    0.72
    0.72
     NIM
    0.69
     OPPO
    0.69
    od
    0.68
     KYC
    0.68
    us
    0.68
     t
    0.67
    POSITIVE LOGITS
    した
    0.72
    お金
    0.67
    ре
    0.65
     zeigte
    0.64
     montrent
    0.63
     zeigen
    0.61
    e
    0.61
    ερμαν
    0.61
    お子
    0.60
    ある
    0.59
    Act Density 0.092%

    No Known Activations