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

    Neuronpedia

    INDEX
    Explanations

    private

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ಇದೇ
    -0.08
     ukuba
    -0.08
     coal
    -0.08
    Coal
    -0.07
     दिनों
    -0.07
     ODI
    -0.07
     days
    -0.07
     اسرائی
    -0.07
     Paying
    -0.07
     riječ
    -0.07
    POSITIVE LOGITS
    .Repository
    0.08
    লি
    0.08
     hides
    0.08
     barred
    0.08
     barriers
    0.07
     puertas
    0.07
    .Private
    0.07
     الباب
    0.07
    운
    0.07
    uzzi
    0.07
    Act Density 0.003%

    No Known Activations