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

    Neuronpedia

    INDEX
    Explanations

    code structure or code syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     for
    1.08
    т
    1.00
    ES
    0.95
     are
    0.91
    ی
    0.89
    CAST
    0.88
    CHRIST
    0.87
    el
    0.86
    :
    0.86
    on
    0.86
    POSITIVE LOGITS
     médiocrement
    0.84
     reação
    0.77
     μία
    0.73
     ખાસ
    0.71
    αν
    0.68
     jaunâtre
    0.68
    மாக
    0.67
    uição
    0.66
     necessário
    0.66
     هایی
    0.66
    Act Density 0.000%

    No Known Activations