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

    Neuronpedia

    INDEX
    Explanations

    than

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Execution
    -0.08
    明明
    -0.07
    Luck
    -0.07
    .GetMapping
    -0.07
     inspection
    -0.07
    濠
    -0.07
     adequately
    -0.07
     deduction
    -0.07
    梆
    -0.07
    质量问题
    -0.07
    POSITIVE LOGITS
    AtPath
    0.07
    ters
    0.07
    WithDuration
    0.07
    (product
    0.07
    oran
    0.07
    גורם
    0.06
     عام
    0.06
    or
    0.06
    aeper
    0.06
    ATOR
    0.06
    Act Density 0.016%

    No Known Activations