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

    Neuronpedia

    INDEX
    Explanations

    bread, cat, dog, pizza ingredients

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ан
    1.02
    Đặt
    1.02
    ان
    1.00
    İN
    1.00
    ઝ
    0.97
    િંગ
    0.95
    크
    0.95
    ات
    0.89
    پ
    0.89
     boissons
    0.88
    POSITIVE LOGITS
    ll
    1.05
    st
    1.02
     layers
    0.99
    llis
    0.99
     Integrative
    0.98
    ness
    0.97
    der
    0.93
    lles
    0.93
    stown
    0.92
    stå
    0.92
    Act Density 0.000%

    No Known Activations