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

    Neuronpedia

    INDEX
    Explanations

    big

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dataset
    -0.07
    нич
    -0.07
     academy
    -0.07
    화를
    -0.07
     alumno
    -0.07
     codigo
    -0.07
     ліка
    -0.07
    acao
    -0.07
    lín
    -0.06
     blends
    -0.06
    POSITIVE LOGITS
    )f
    0.07
     خانو
    0.06
     आग
    0.06
    parseInt
    0.06
    /internal
    0.05
    _height
    0.05
     unten
    0.05
    Fixture
    0.05
    ‐‐
    0.05
    ...
↵
    0.05
    Act Density 0.010%

    No Known Activations