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

    Neuronpedia

    INDEX
    Explanations

    examples

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Dados
    -0.06
    ください
    -0.06
    arlo
    -0.06
     curb
    -0.06
     Си
    -0.06
     ích
    -0.06
     zombie
    -0.06
     devastation
    -0.06
     promoter
    -0.06
     rightfully
    -0.06
    POSITIVE LOGITS
    Alan
    0.07
    tener
    0.06
    -random
    0.06
    忘
    0.06
    ΟΦ
    0.06
     Alan
    0.06
    ospace
    0.06
    าส
    0.06
    getColor
    0.06
    _VE
    0.06
    Act Density 0.001%

    No Known Activations