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

    Neuronpedia

    INDEX
    Explanations

    family= in urls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ные
    0.98
    rés
    0.98
    ación
    0.91
    ется
    0.86
    )
    0.85
    ።
    0.85
    ését
    0.83
    resión
    0.80
    ról
    0.80
    ilación
    0.79
    POSITIVE LOGITS
     (
    1.52
     to
    1.23
    {
    0.91
    𝓰
    0.81
     with
    0.80
    ผู้
    0.80
    N
    0.78
     it
    0.77
    CON
    0.76
    WITH
    0.75
    Act Density 0.004%

    No Known Activations