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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Define
    -0.07
     follower
    -0.06
    种
    -0.06
    ším
    -0.06
     बय
    -0.06
     (+
    -0.06
    ./
    -0.06
    ynos
    -0.06
    	error
    -0.06
     NSDictionary
    -0.06
    POSITIVE LOGITS
    WARN
    0.07
    buzz
    0.07
    anzi
    0.07
    _flux
    0.07
    lst
    0.07
     อำเภ
    0.06
    TZ
    0.06
    ôme
    0.06
     Alliance
    0.06
    уди
    0.06
    Act Density 0.167%

    No Known Activations