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

    Neuronpedia

    INDEX
    Explanations

    dog breeds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hem
    -0.08
    チン
    -0.07
    updated
    -0.07
     Stephen
    -0.07
    >'
    -0.07
     ת
    -0.06
    eparator
    -0.06
    咄
    -0.06
    Portrait
    -0.06
     Gun
    -0.06
    POSITIVE LOGITS
     объявл
    0.08
     שלך
    0.07
    只怕
    0.07
     Experts
    0.06
    acellular
    0.06
     serão
    0.06
    cret
    0.06
    classify
    0.06
     ruth
    0.06
    疤痕
    0.06
    Act Density 0.004%

    No Known Activations