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

    Neuronpedia

    INDEX
    Explanations

    $(

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sailed
    -0.08
    izzare
    -0.07
    携程
    -0.07
    imesteps
    -0.07
     Vì
    -0.07
     getCode
    -0.07
    Magn
    -0.07
    ANCE
    -0.07
     zamówienia
    -0.07
    Val
    -0.07
    POSITIVE LOGITS
    ープ
    0.08
     settlements
    0.07
    <[
    0.06
    归属于
    0.06
     ابن
    0.06
    شرف
    0.06
     Establishment
    0.06
    .shutdown
    0.06
    _dark
    0.06
    侵害
    0.06
    Act Density 0.004%

    No Known Activations