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

    Neuronpedia

    INDEX
    Explanations

    Domestic Violence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     affirmatively
    0.70
     shores
    0.69
     unquestionably
    0.63
     nobody
    0.60
    шками
    0.59
     pentru
    0.59
     исключительно
    0.59
     admirably
    0.59
     aprobar
    0.58
     ausschließlich
    0.58
    POSITIVE LOGITS
     ofthe
    0.70
    मैं
    0.68
    /
    0.64
    of
    0.64
    ితే
    0.63
     of
    0.63
     ਅਤੇ
    0.60
     ή
    0.58
    ະລ
    0.57
    または
    0.57
    Act Density 0.019%

    No Known Activations