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

    Neuronpedia

    INDEX
    Explanations

    license or license selection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ertura
    1.84
    ोग
    1.82
    nT
    1.80
    table
    1.78
    icrobial
    1.75
    Фу
    1.72
    mathrm
    1.71
    opoietic
    1.70
    iev
    1.66
    iej
    1.64
    POSITIVE LOGITS
    т
    1.91
    ਰ
    1.91
    ও
    1.84
    ją
    1.80
    ভিত্তিক
    1.77
    のかもし
    1.73
     straordin
    1.72
     ולא
    1.71
    ض
    1.70
    зі
    1.69
    Act Density 0.012%

    No Known Activations