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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     translating
    -0.06
     backgroundColor
    -0.06
     independently
    -0.06
     cable
    -0.06
     treating
    -0.06
    вей
    -0.06
    emmel
    -0.06
     ث
    -0.06
    _diag
    -0.06
     computation
    -0.06
    POSITIVE LOGITS
    Sugar
    0.07
    joining
    0.07
    adders
    0.07
    増
    0.07
    条件
    0.07
    ategies
    0.06
    DbContext
    0.06
    LERİ
    0.06
    аніт
    0.06
    BREAK
    0.06
    Act Density 0.004%

    No Known Activations