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

    Neuronpedia

    INDEX
    Explanations

    risk factors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (
    0.76
    يد
    0.70
    ER
    0.66
    UM
    0.66
    AT
    0.65
    EX
    0.65
     premiere
    0.61
    েন
    0.61
    ньше
    0.61
    Aqui
    0.61
    POSITIVE LOGITS
     tật
    0.73
    o
    0.73
    ૧
    0.73
    ೧
    0.71
    definitions
    0.70
    饰
    0.70
    factors
    0.70
    рка
    0.67
     제작
    0.67
     دھو
    0.66
    Act Density 0.004%

    No Known Activations