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

    Neuronpedia

    INDEX
    Explanations

    Text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    zek
    -0.07
     إلي
    -0.07
    حية
    -0.07
    zę
    -0.07
    isté
    -0.06
    ач
    -0.06
     تای
    -0.06
    čné
    -0.06
     níž
    -0.06
    yna
    -0.06
    POSITIVE LOGITS
     attributes
    0.07
    .arguments
    0.07
     obs
    0.06
    ended
    0.06
    asonry
    0.06
     absorbing
    0.06
    岛
    0.06
    pciones
    0.06
    销售
    0.06
    Reviews
    0.06
    Act Density 0.000%

    No Known Activations