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

    Neuronpedia

    INDEX
    Explanations

    code and mathematics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     accumulation
    -0.07
    ضاء
    -0.07
    nage
    -0.07
     Χ
    -0.06
     Dimensions
    -0.06
     calories
    -0.06
    ã
    -0.06
    职业
    -0.06
     Mental
    -0.06
     mili
    -0.06
    POSITIVE LOGITS
    政
    0.06
     terrific
    0.06
    ----------↵
    0.06
    .JsonProperty
    0.06
    .URL
    0.06
    用于
    0.06
    .Interop
    0.06
     трен
    0.06
    .yaml
    0.05
    OptionsMenu
    0.05
    Act Density 0.000%

    No Known Activations