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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PREF
    -0.07
    interpret
    -0.06
     رم
    -0.06
    बर
    -0.06
     theat
    -0.06
     phản
    -0.06
     he
    -0.06
    inning
    -0.06
    (()
    -0.06
    虽然
    -0.06
    POSITIVE LOGITS
     Bölgesi
    0.07
    URLOPT
    0.06
     başlat
    0.06
     zastav
    0.06
    Overrides
    0.06
    /terms
    0.06
    EGIN
    0.06
     Newtonsoft
    0.06
    ,length
    0.06
    _metric
    0.06
    Act Density 0.013%

    No Known Activations