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

    Neuronpedia

    INDEX
    Explanations

    mathematical operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    צ
    0.99
    ل
    0.98
    ка
    0.90
    ა
    0.88
    ബ
    0.86
    ด
    0.83
    па
    0.82
    е
    0.79
    м
    0.79
    ন
    0.79
    POSITIVE LOGITS
     Davos
    0.88
    فة
    0.87
     gtag
    0.84
    abhave
    0.79
    ição
    0.78
     detriment
    0.78
    irit
    0.77
    yes
    0.76
     vada
    0.74
    opss
    0.73
    Act Density 0.165%

    No Known Activations