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

    Neuronpedia

    INDEX
    Explanations

    parent or guardian rights

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Мы
    0.49
    Мы
    0.48
     الل
    0.47
    م
    0.46
    <0xD9>
    0.46
    מיד
    0.45
     मंत्रिम
    0.45
    مک
    0.45
     عندما
    0.44
     europé
    0.44
    POSITIVE LOGITS
    o
    0.52
    es
    0.52
    an
    0.49
    ́t
    0.46
     Whose
    0.45
    enciar
    0.44
    ono
    0.43
    on
    0.43
    onio
    0.42
     lottery
    0.42
    Act Density 0.001%

    No Known Activations