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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     algunas
    -0.07
     hs
    -0.07
    addAll
    -0.06
    Kh
    -0.06
     captains
    -0.06
    ctx
    -0.06
    .”↵↵
    -0.06
    .publish
    -0.06
    兄弟
    -0.06
    ...";↵
    -0.06
    POSITIVE LOGITS
    _HW
    0.07
     무슨
    0.07
     Pol
    0.06
     Feder
    0.06
     وا
    0.06
     đăng
    0.06
     humili
    0.06
    _snd
    0.06
    ViewModel
    0.06
     Нат
    0.06
    Act Density 0.065%

    No Known Activations