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

    Neuronpedia

    INDEX
    Explanations

    requirements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Мик
    -0.07
     เด
    -0.07
    .raw
    -0.07
    cyan
    -0.07
    _mobile
    -0.07
     طريق
    -0.06
    _visitor
    -0.06
    _STANDARD
    -0.06
    tır
    -0.06
    іть
    -0.06
    POSITIVE LOGITS
    Conditional
    0.07
     допомоги
    0.07
    ужд
    0.06
    (score
    0.06
     Зав
    0.06
    _AC
    0.06
     Ellie
    0.06
    (class
    0.06
     непосред
    0.06
     Springer
    0.06
    Act Density 0.076%

    No Known Activations