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

    Neuronpedia

    INDEX
    Explanations

    say "stop"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     koşul
    -0.07
     Dance
    -0.07
     کان
    -0.06
    имер
    -0.06
    普通
    -0.06
    .Fetch
    -0.06
    683
    -0.06
    眼
    -0.06
     Ear
    -0.06
     Mutex
    -0.06
    POSITIVE LOGITS
    -by
    0.07
     SCHOOL
    0.07
     physicist
    0.06
    brities
    0.06
    (&_
    0.06
     physicists
    0.06
    ениями
    0.06
     myth
    0.06
     cognitive
    0.06
    وست
    0.06
    Act Density 0.022%

    No Known Activations