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

    Neuronpedia

    INDEX
    Explanations

    archetypes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ing
    1.15
     cria
    0.96
    的
    0.94
    ла
    0.90
    اد
    0.89
    ное
    0.88
    p
    0.88
    ang
    0.86
    ও
    0.85
    um
    0.83
    POSITIVE LOGITS
    ,=
    0.80
    )&=
    0.77
    \/}
    0.76
     Arche
    0.74
    ,\\
    0.73
     archetype
    0.71
    CellValue
    0.70
     этапе
    0.69
    )"))
    0.68
    )‏
    0.68
    Act Density 0.001%

    No Known Activations