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

    Neuronpedia

    INDEX
    Explanations

    want freedom verbatim

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     playerCards
    0.44
    retrieve
    0.43
    ovane
    0.43
    ין
    0.41
     plastik
    0.41
    ردن
    0.40
     qilish
    0.39
    istič
    0.38
    тена
    0.38
     балко
    0.38
    POSITIVE LOGITS
     identifying
    0.40
     Preparing
    0.40
    pricing
    0.38
     identify
    0.38
     விரும்ப
    0.38
     Schools
    0.37
     preparing
    0.37
    xi
    0.35
     Büh
    0.35
     poet
    0.35
    Act Density 0.000%

    No Known Activations