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

    Neuronpedia

    INDEX
    Explanations

    -sectional

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ah
    -0.07
    เส
    -0.06
     entrada
    -0.06
     expres
    -0.06
    어요
    -0.06
     Buenos
    -0.06
     reverence
    -0.06
    める
    -0.06
     tenemos
    -0.06
    (match
    -0.06
    POSITIVE LOGITS
    SOR
    0.07
    ,title
    0.07
    .Execution
    0.07
     सकत
    0.07
     interdisciplinary
    0.07
    ENCED
    0.07
    _LABEL
    0.07
     Bison
    0.07
     iceberg
    0.06
    achte
    0.06
    Act Density 0.002%

    No Known Activations