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

    Neuronpedia

    INDEX
    Explanations

    Javascript

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Write
    -0.07
     cư
    -0.07
     hrs
    -0.07
    akh
    -0.07
    -match
    -0.07
     Rel
    -0.07
    itic
    -0.06
    (lang
    -0.06
    用品
    -0.06
    行為
    -0.06
    POSITIVE LOGITS
     boils
    0.07
    Stories
    0.07
    .getSelectionModel
    0.07
    جائ
    0.07
     sadness
    0.07
    火焰
    0.07
    的真实
    0.07
     healer
    0.07
    藍
    0.06
    넑
    0.06
    Act Density 0.001%

    No Known Activations