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

    Neuronpedia

    INDEX
    Explanations

    JavaScript library imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ج
    0.80
     actuel
    0.76
     comprim
    0.73
    ش
    0.73
    ق
    0.73
     зала
    0.71
    ية
    0.70
     sicuro
    0.70
     futuro
    0.69
     pyram
    0.68
    POSITIVE LOGITS
    G
    0.95
    B
    0.89
    Ž
    0.89
    M
    0.83
    Ş
    0.83
    D
    0.82
    Z
    0.82
    O
    0.80
    T
    0.77
    Ż
    0.76
    Act Density 0.015%

    No Known Activations