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

    Neuronpedia

    INDEX
    Explanations

    stop words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MainThread
    -0.08
    ivid
    -0.07
     crossing
    -0.07
     excitement
    -0.06
    imen
    -0.06
    汇
    -0.06
    бав
    -0.06
     het
    -0.06
    _TAB
    -0.06
    mitted
    -0.06
    POSITIVE LOGITS
     atheists
    0.07
    스티
    0.06
    เค
    0.06
    ItemAt
    0.06
    ,test
    0.06
    exao
    0.06
     Москов
    0.06
     الحديث
    0.06
     Russia
    0.06
    elsinki
    0.06
    Act Density 0.072%

    No Known Activations