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

    Neuronpedia

    INDEX
    Explanations

    slashes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    some
    -0.07
     bred
    -0.07
    (key
    -0.07
     núi
    -0.07
    (sh
    -0.07
    symbols
    -0.07
    original
    -0.07
    mock
    -0.07
    pressed
    -0.06
    Leg
    -0.06
    POSITIVE LOGITS
     органов
    0.07
    _GB
    0.06
     مدينة
    0.06
    .backward
    0.06
     posicion
    0.06
    _SUM
    0.06
    िकट
    0.06
    しても
    0.06
     Cobb
    0.06
    lor
    0.06
    Act Density 0.006%

    No Known Activations