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

    Neuronpedia

    INDEX
    Explanations

    Music and synthesizers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _lang
    -0.09
     ing
    -0.08
    lang
    -0.08
    Mileage
    -0.07
    Lang
    -0.07
     overl
    -0.07
     servings
    -0.07
     low
    -0.07
    aining
    -0.07
    Nutrition
    -0.07
    POSITIVE LOGITS
    振
    0.09
    SED
    0.08
     ರೀತ
    0.08
     Naughty
    0.08
    usic
    0.08
    ирован
    0.08
     Duty
    0.07
     favorita
    0.07
    ffects
    0.07
    ございました
    0.07
    Act Density 0.000%

    No Known Activations