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

    Neuronpedia

    INDEX
    Explanations

    Initials and Names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    оля
    -0.07
     dbl
    -0.07
    haf
    -0.06
    固
    -0.06
    HORT
    -0.06
     гара
    -0.06
    (KEY
    -0.06
    तर
    -0.06
     Кар
    -0.06
    렸
    -0.06
    POSITIVE LOGITS
    ialias
    0.07
    locales
    0.07
    fs
    0.06
    FS
    0.06
    angling
    0.06
     iceberg
    0.06
    anoi
    0.06
    .guild
    0.06
    creates
    0.06
    accuracy
    0.06
    Act Density 0.004%

    No Known Activations