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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    似乎
    -0.08
    chedules
    -0.06
    ubbo
    -0.06
    _literal
    -0.06
    увати
    -0.06
    'un
    -0.06
     miracle
    -0.06
     mesaj
    -0.06
     часто
    -0.06
    ’nin
    -0.06
    POSITIVE LOGITS
    색
    0.07
    õ
    0.07
    .ViewModels
    0.07
    USIC
    0.06
     databases
    0.06
    .theta
    0.06
    /html
    0.06
    arking
    0.06
    expression
    0.06
     alc
    0.06
    Act Density 0.044%

    No Known Activations