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

    Neuronpedia

    INDEX
    Explanations

    company and country names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    r
    1.23
    ر
    1.22
    c
    1.02
    ა
    1.00
    ah
    0.97
    á
    0.95
    f
    0.95
    s
    0.94
    ка
    0.93
    b
    0.91
    POSITIVE LOGITS
     année
    0.83
     реали
    0.78
    WIDE
    0.78
    व्यापी
    0.78
    🈶
    0.77
    ━━━━━━━━
    0.76
     الداخلية
    0.76
    ﺭ
    0.75
    合わせた
    0.75
    ┎
    0.75
    Act Density 0.204%

    No Known Activations