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

    Neuronpedia

    INDEX
    Explanations

    MySQL tables and errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    感慨
    -0.09
     predictions
    -0.08
    كون
    -0.07
     RETURN
    -0.07
    /scripts
    -0.07
     VIS
    -0.07
     measure
    -0.07
    (spec
    -0.07
    wm
    -0.07
     ----------------------------------------------------------------------------------------------------------------
    -0.07
    POSITIVE LOGITS
    之旅
    0.08
     dishonest
    0.07
    햊
    0.07
    ספר
    0.07
     getaway
    0.07
    抢先
    0.07
     eag
    0.06
    -rise
    0.06
     fares
    0.06
    sembles
    0.06
    Act Density 0.002%

    No Known Activations