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

    Neuronpedia

    INDEX
    Explanations

    wordpress plugin named

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    yenne
    0.44
    ಲಿದೆ
    0.44
    ಬ್ಬಿಣ
    0.42
     $.
    0.41
    dados
    0.40
    copyright
    0.40
    σουμε
    0.40
    amatsu
    0.40
     saker
    0.39
     valable
    0.39
    POSITIVE LOGITS
    ["
    0.44
     də
    0.43
     both
    0.42
     localVarAccept
    0.42
    [
    0.41
    ['
    0.41
    uesto
    0.41
     balances
    0.41
    [(
    0.40
     Guilty
    0.40
    Act Density 0.000%

    No Known Activations