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

    Neuronpedia

    INDEX
    Explanations

    Negative language/profanity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	operator
    -0.07
     Dataset
    -0.06
     mpz
    -0.06
     комп
    -0.06
     сер
    -0.06
    aucoup
    -0.06
    (nc
    -0.06
     소
    -0.06
     Cain
    -0.06
    vailability
    -0.06
    POSITIVE LOGITS
    168
    0.07
     mostly
    0.07
    .XtraPrinting
    0.07
    FormsModule
    0.07
     Gazette
    0.06
    FromFile
    0.06
    finally
    0.06
     trava
    0.06
    _rl
    0.06
     perhaps
    0.06
    Act Density 0.017%

    No Known Activations