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

    Neuronpedia

    INDEX
    Explanations

    exceptions or contrasting statements.

    oai_token-act-pair · gemini-2.0-flash

    conjunctions, punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    OGND
    -0.72
     Normdatei
    -0.71
     '\\;'
    -0.68
    ScopeManager
    -0.67
    UpInside
    -0.65
     Wikimedijinoj
    -0.63
    InitStruct
    -0.61
     NSCoder
    -0.61
    GEBURTSDATUM
    -0.60
     المعيارى
    -0.60
    POSITIVE LOGITS
    //
    0.58
    Література
    0.55
    zają
    0.45
    nologies
    0.45
    chure
    0.44
     contin
    0.44
     stomat
    0.43
    ukkig
    0.43
     hopeful
    0.41
    ategorien
    0.41
    Act Density 0.685%

    No Known Activations