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

    Neuronpedia

    INDEX
    Explanations

    Numerical IDs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _VM
    -0.07
     Sullivan
    -0.07
     convolution
    -0.07
     þ
    -0.07
     traction
    -0.07
     processing
    -0.06
     Practices
    -0.06
     Pipeline
    -0.06
     Aircraft
    -0.06
    _operator
    -0.06
    POSITIVE LOGITS
    ,self
    0.08
    钱币
    0.07
    瘌
    0.07
    ~
    0.07
    ')}↵
    0.07
    调查显示
    0.07
    瞪
    0.06
    (\'
    0.06
    coef
    0.06
    specialchars
    0.06
    Act Density 0.009%

    No Known Activations