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

    Neuronpedia

    INDEX
    Explanations

    definition

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DataExchange
    -0.07
     DataBase
    -0.07
     citas
    -0.07
    Judge
    -0.07
     behaviour
    -0.07
    一日
    -0.07
    芒果
    -0.07
    mse
    -0.06
    ó
    -0.06
    integr
    -0.06
    POSITIVE LOGITS
    yling
    0.07
    買う
    0.07
    蟀
    0.07
    .encoding
    0.07
    oli
    0.07
     hills
    0.07
    ymb
    0.06
     sonic
    0.06
    ulf
    0.06
     maçı
    0.06
    Act Density 0.050%

    No Known Activations