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

    Neuronpedia

    INDEX
    Explanations

    U

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _permissions
    -0.07
    super
    -0.06
    quet
    -0.06
     dirt
    -0.06
     grandparents
    -0.06
     args
    -0.06
     Holt
    -0.06
    -bound
    -0.06
    580
    -0.06
     Hour
    -0.06
    POSITIVE LOGITS
    طف
    0.07
    ibilidad
    0.07
     seated
    0.06
     —↵↵
    0.06
    ्ययन
    0.06
     faaliyet
    0.06
    ोब
    0.06
    arat
    0.06
    SES
    0.06
     hâlâ
    0.06
    Act Density 0.034%

    No Known Activations