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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cruz
    -0.07
     Нет
    -0.06
    ifold
    -0.06
    олов
    -0.06
    Definition
    -0.06
    >--}}↵
    -0.06
     Sad
    -0.06
    орм
    -0.06
    (cc
    -0.06
    ifu
    -0.06
    POSITIVE LOGITS
     Contrib
    0.07
    Texto
    0.07
    uated
    0.07
     انقل
    0.07
     gebru
    0.06
     옆
    0.06
     والت
    0.06
    ag
    0.06
     translated
    0.06
    ashing
    0.06
    Act Density 0.146%

    No Known Activations