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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lawyers
    -0.07
    。但
    -0.07
     ως
    -0.06
    ;m
    -0.06
    epend
    -0.06
     are
    -0.06
    __;↵
    -0.06
    상담
    -0.06
    TestClass
    -0.06
     obstruction
    -0.06
    POSITIVE LOGITS
     esper
    0.07
     ї
    0.07
    leta
    0.06
    javax
    0.06
    reservation
    0.06
    _IA
    0.06
     RFID
    0.06
    	cerr
    0.06
    _chip
    0.06
    riminator
    0.06
    Act Density 0.007%

    No Known Activations