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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     дво
    -0.07
    .pick
    -0.06
    minimal
    -0.06
     Güven
    -0.06
    Failure
    -0.06
    ──
    -0.06
    .find
    -0.06
    .one
    -0.06
     Beginner
    -0.06
     Produto
    -0.06
    POSITIVE LOGITS
     il
    0.07
     заболевания
    0.07
     San
    0.07
     helped
    0.06
     많은
    0.06
    ucht
    0.06
    �이
    0.06
     активно
    0.06
     ents
    0.06
    entious
    0.06
    Act Density 0.066%

    No Known Activations