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

    Neuronpedia

    INDEX
    Explanations

    classNames names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	a
    -0.08
    +'/'+
    -0.08
    .spinner
    -0.07
     Nga
    -0.07
     wasn
    -0.07
    got
    -0.07
    Sou
    -0.07
     koji
    -0.07
     ape
    -0.07
     Python
    -0.07
    POSITIVE LOGITS
    UCCESS
    0.07
    驾
    0.06
    聽
    0.06
    -hash
    0.06
    letic
    0.06
     Bradley
    0.06
    _SETTINGS
    0.06
    Information
    0.06
    .SIZE
    0.05
    contents
    0.05
    Act Density 0.003%

    No Known Activations