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

    Neuronpedia

    INDEX
    Explanations

    months

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ARIANT
    -0.07
    교회
    -0.07
     pornô
    -0.07
     Tie
    -0.07
    	So
    -0.06
     Evo
    -0.06
    .LocalDate
    -0.06
    787
    -0.06
     sexle
    -0.06
     edecek
    -0.06
    POSITIVE LOGITS
    _abort
    0.07
     stri
    0.06
     elevated
    0.06
     ان
    0.06
     пр
    0.06
    _sign
    0.06
     scient
    0.06
    infer
    0.06
    _str
    0.06
    极
    0.06
    Act Density 0.003%

    No Known Activations