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

    Neuronpedia

    INDEX
    Explanations

    callback and bond

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ла
    0.71
    都
    0.69
    .
    0.64
    са
    0.64
    त
    0.63
    а
    0.62
    ered
    0.56
    ור
    0.55
    ethe
    0.55
    б
    0.55
    POSITIVE LOGITS
     fodder
    0.62
     flashbacks
    0.56
     handouts
    0.55
     slogans
    0.54
     budgets
    0.54
    moires
    0.52
     remake
    0.52
     MLAs
    0.52
     Crafted
    0.52
     Saturdays
    0.52
    Act Density 0.000%

    No Known Activations