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

    Neuronpedia

    INDEX
    Explanations

    voltage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uccio
    0.82
    izzano
    0.72
    庐
    0.71
     località
    0.70
    ী
    0.70
    ไม้
    0.70
     ст
    0.69
    вні
    0.69
     різних
    0.69
     mitosis
    0.69
    POSITIVE LOGITS
    ng
    1.02
    en
    0.91
    w
    0.89
    7
    0.85
    5
    0.84
    ड्र
    0.82
    ii
    0.82
    n
    0.81
    y
    0.80
    1
    0.79
    Act Density 0.000%

    No Known Activations