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

    Neuronpedia

    INDEX
    Explanations

    words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ado
    -0.07
     Owned
    -0.07
    NS
    -0.07
    活
    -0.07
     ALS
    -0.07
     의
    -0.07
     ethanol
    -0.07
    HC
    -0.07
    初始化
    -0.07
     funded
    -0.07
    POSITIVE LOGITS
    (argc
    0.07
     nods
    0.07
    留住
    0.07
    .DropTable
    0.07
     Başkan
    0.07
     lesions
    0.07
    身创造
    0.06
     Ça
    0.06
    optgroup
    0.06
     Phonetic
    0.06
    Act Density 0.009%

    No Known Activations