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

    Neuronpedia

    INDEX
    Explanations

    file extensions and domain names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    P
    1.00
    C
    0.97
     solcher
    0.96
     ergän
    0.93
     höchste
    0.92
     Abbiamo
    0.91
     olefin
    0.89
     Jeżeli
    0.88
     essendo
    0.87
     schön
    0.86
    POSITIVE LOGITS
    на
    1.20
    ان
    1.00
    ли
    0.98
    ೂ
    0.93
    aiian
    0.90
    이트
    0.89
    ୯
    0.89
    ל
    0.88
    но
    0.87
    膛
    0.86
    Act Density 0.092%

    No Known Activations