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

    Neuronpedia

    INDEX
    Explanations

    data extraction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hib
    -0.08
    ضم
    -0.07
     Scotia
    -0.06
    .Observer
    -0.06
     bunları
    -0.06
    ุมภาพ
    -0.06
     dared
    -0.06
    ymology
    -0.06
    _failed
    -0.06
     Saudi
    -0.06
    POSITIVE LOGITS
     */↵↵↵
    0.06
     autumn
    0.06
     Erotic
    0.06
    ۱۴
    0.06
    –↵↵
    0.06
     است
    0.06
     cr
    0.06
     Evening
    0.06
     ends
    0.06
     Clients
    0.06
    Act Density 0.000%

    No Known Activations