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

    Neuronpedia

    INDEX
    Explanations

    Short text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ******
    -0.07
     مك
    -0.07
    Mocks
    -0.06
     Insets
    -0.06
     God
    -0.06
     stav
    -0.06
    _sprites
    -0.06
     tặng
    -0.06
    项目
    -0.06
     미
    -0.06
    POSITIVE LOGITS
    ерта
    0.06
    ahrungen
    0.06
     Which
    0.06
    ेयर
    0.06
    awaii
    0.06
     علاق
    0.06
    サービス
    0.06
     expenses
    0.06
    .intersection
    0.05
    .hwp
    0.05
    Act Density 0.000%

    No Known Activations