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

    Neuronpedia

    INDEX
    Explanations

    NDA coalition unity Order election government

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Aquí
    0.70
    تي
    0.61
     القسم
    0.61
    डमी
    0.61
    čkom
    0.59
    انى
    0.58
     училище
    0.58
     kurze
    0.57
     الموسم
    0.57
    тка
    0.57
    POSITIVE LOGITS
    have
    0.68
    ेंस
    0.55
    bl
    0.53
     have
    0.52
    iden
    0.49
    िएट
    0.49
    <0xE9>
    0.48
    ands
    0.48
    controlling
    0.48
    fulness
    0.47
    Act Density 0.000%

    No Known Activations