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

    Neuronpedia

    INDEX
    Explanations

    grade

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     모습
    -0.09
     Пом
    -0.07
    monary
    -0.07
     INTO
    -0.07
     яв
    -0.07
     Ont
    -0.06
     tự
    -0.06
     RESPONS
    -0.06
    EventManager
    -0.06
     contemplating
    -0.06
    POSITIVE LOGITS
     grade
    0.08
    Grade
    0.07
    gsub
    0.06
     grammar
    0.06
     Grade
    0.06
     Griff
    0.06
     grind
    0.06
    cheap
    0.06
    Type
    0.06
     maxlength
    0.06
    Act Density 0.006%

    No Known Activations