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

    Neuronpedia

    INDEX
    Explanations

    and confidential

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    turno
    0.39
    вно
    0.38
    iseaux
    0.38
    rete
    0.38
    并在
    0.38
    ито
    0.38
    ADOR
    0.38
    োদয়
    0.37
    ীয়তে
    0.37
    ICIO
    0.37
    POSITIVE LOGITS
     carriages
    0.38
     stimmen
    0.37
     notices
    0.37
    唐
    0.35
    ذ
    0.35
    佾
    0.35
     anonymous
    0.34
     anonymity
    0.34
    ਣਾ
    0.34
    ੰ
    0.34
    Act Density 0.003%

    No Known Activations