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

    Neuronpedia

    INDEX
    Explanations

    9

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Horizontal
    -0.06
    .contrib
    -0.06
     kterou
    -0.06
    .IOException
    -0.06
    Seg
    -0.06
     dab
    -0.06
    .en
    -0.06
     đá
    -0.06
     finalist
    -0.06
    ادر
    -0.06
    POSITIVE LOGITS
     个
    0.07
     комплекс
    0.07
    تز
    0.06
     greatly
    0.06
    .Matrix
    0.06
     ];↵↵
    0.06
    χα
    0.06
    .organization
    0.06
     submit
    0.06
    -blog
    0.06
    Act Density 0.001%

    No Known Activations