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

    Neuronpedia

    INDEX
    Explanations

    Polish words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ACION
    -0.12
    ACIONES
    -0.11
    acions
    -0.09
     ace
    -0.09
    ATIO
    -0.09
    ACIÓN
    -0.09
    acas
    -0.08
    aciones
    -0.08
    ácio
    -0.08
    aces
    -0.08
    POSITIVE LOGITS
    yc
    0.13
    ję
    0.12
    cyj
    0.12
    cj
    0.12
    c
    0.12
    cji
    0.11
    cja
    0.11
    y
    0.10
    cy
    0.09
    bic
    0.09
    Act Density 0.002%

    No Known Activations