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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rack
    -0.07
    igor
    -0.07
    uth
    -0.07
     Bellev
    -0.06
     mey
    -0.06
    Spe
    -0.06
    arel
    -0.06
     Tears
    -0.06
    boat
    -0.06
    كم
    -0.06
    POSITIVE LOGITS
     safest
    0.07
    \brief
    0.06
    leyin
    0.06
     použít
    0.06
    уска
    0.06
    ,out
    0.06
    ::*;↵
    0.06
    ◎
    0.06
    ının
    0.06
    галтер
    0.06
    Act Density 0.001%

    No Known Activations