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

    Neuronpedia

    INDEX
    Explanations

    Properties

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     زمانی
    -0.07
    servername
    -0.07
    BUS
    -0.06
    .columnHeader
    -0.06
     itibaren
    -0.06
     tiế
    -0.06
     potom
    -0.06
    Scene
    -0.06
     avanz
    -0.06
    가
    -0.06
    POSITIVE LOGITS
     Stim
    0.07
     دریافت
    0.06
    sequently
    0.06
    交通
    0.06
    examples
    0.06
    렸
    0.05
    梨
    0.05
    质量
    0.05
    öy
    0.05
    (CONFIG
    0.05
    Act Density 0.004%

    No Known Activations