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

    Neuronpedia

    INDEX
    Explanations

    br

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ніп
    -0.07
    sales
    -0.07
     ucwords
    -0.06
     hann
    -0.06
    urus
    -0.06
    Merit
    -0.06
     pow
    -0.06
     rave
    -0.06
    орів
    -0.06
    Match
    -0.06
    POSITIVE LOGITS
    สภ
    0.08
    -reset
    0.07
     област
    0.07
    adresse
    0.07
     LocalDate
    0.06
     rece
    0.06
     sécurité
    0.06
    rejected
    0.06
    _lb
    0.06
    оза
    0.06
    Act Density 0.006%

    No Known Activations