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

    Neuronpedia

    INDEX
    Explanations

    find "="

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pela
    0.42
    ক্সি
    0.42
    ក្ខ
    0.39
     costes
    0.39
     instit
    0.38
    igts
    0.38
    piej
    0.38
    sej
    0.38
    int
    0.37
    quia
    0.37
    POSITIVE LOGITS
     Signals
    0.40
    ében
    0.40
    鳶
    0.39
     komentar
    0.37
    socketState
    0.37
     béton
    0.37
    醌
    0.37
    ల్‌
    0.36
    Batman
    0.36
    otard
    0.36
    Act Density 0.000%

    No Known Activations