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
    技能
    -0.07
     brave
    -0.07
     conscience
    -0.06
     Teil
    -0.06
    Lookup
    -0.06
     khí
    -0.06
     Particip
    -0.06
     Chevrolet
    -0.06
    εδ
    -0.06
     literary
    -0.06
    POSITIVE LOGITS
    NST
    0.07
     ผล
    0.06
    شماری
    0.06
    /epl
    0.06
    ":-
    0.06
    ZH
    0.06
    (push
    0.06
     devise
    0.06
    “In
    0.06
     είχαν
    0.06
    Act Density 0.059%

    No Known Activations