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

    Neuronpedia

    INDEX
    Explanations

    chamber of commerce

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1.18
    nis
    0.95
    ن
    0.92
    ts
    0.90
    P
    0.88
     It
    0.86
    v
    0.82
    ry
    0.82
    س
    0.80
    ch
    0.79
    POSITIVE LOGITS
    ↵
    1.16
     maio
    1.09
    の
    0.99
    <0x0D>
    0.97
    ма
    0.96
    사
    0.96
    ۹
    0.96
    스트
    0.94
     árboles
    0.94
     społec
    0.93
    Act Density 0.004%

    No Known Activations