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

    Neuronpedia

    INDEX
    Explanations

    overall

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sexkontakte
    -0.07
     must
    -0.07
     sexdate
    -0.06
     spec
    -0.06
    -0.06
     danger
    -0.06
     شود
    -0.06
    (){}↵
    -0.06
    еного
    -0.06
    ्यकत
    -0.06
    POSITIVE LOGITS
     overall
    0.16
    Overall
    0.11
     Overall
    0.11
    overall
    0.11
    aggregate
    0.08
     Oval
    0.08
    	AL
    0.08
    off
    0.08
     holistic
    0.07
     genel
    0.07
    Act Density 0.009%

    No Known Activations