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

    Neuronpedia

    INDEX
    Explanations

    categorized lists with explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,{\
    0.97
     pierwszy
    0.91
     español
    0.90
    [],
    0.90
     parseInt
    0.90
    ܙ
    0.88
     pierwszej
    0.86
     Primero
    0.86
     `<`,
    0.83
     বছর
    0.82
    POSITIVE LOGITS
    ulous
    0.99
    (
    0.98
     until
    0.91
    until
    0.86
     (
    0.86
    ")(
    0.84
    quando
    0.82
     into
    0.82
    matics
    0.77
     terhadap
    0.77
    Act Density 0.041%

    No Known Activations