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

    Neuronpedia

    INDEX
    Explanations

    import", "HOST", "PORT"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ię
    1.19
    例文帳に追加
    1.12
    تش
    1.07
    Ŝ
    1.05
     Paryayvachi
    1.05
     compositional
    1.02
    ق
    1.02
     Необходимо
    0.99
    菘
    0.99
    ط
    0.98
    POSITIVE LOGITS
    పై
    1.11
     in
    1.08
     secondly
    1.06
     also
    1.03
    "":
    1.02
     at
    1.01
     casser
    1.00
     occasione
    1.00
    자를
    0.99
    "
    0.97
    Act Density 0.006%

    No Known Activations