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

    Neuronpedia

    INDEX
    Explanations

    Foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (['/
    -0.08
    ungs
    -0.07
     {"
    -0.07
    分析
    -0.07
    Pwd
    -0.07
    _second
    -0.07
    _sell
    -0.07
    shade
    -0.07
     worthless
    -0.07
    ombres
    -0.06
    POSITIVE LOGITS
    씁
    0.07
     fandom
    0.07
    领会
    0.07
    蕊
    0.07
     להש
    0.07
    滁
    0.06
     śl
    0.06
    .AnchorStyles
    0.06
     fostering
    0.06
    -fontawesome
    0.06
    Act Density 0.087%

    No Known Activations