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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    esses
    -0.07
    ุษ
    -0.06
    /a
    -0.06
     Vas
    -0.06
     TextStyle
    -0.06
     Diy
    -0.06
     ses
    -0.06
    uss
    -0.06
    计划
    -0.06
     центр
    -0.06
    POSITIVE LOGITS
     welcomes
    0.07
     Welcome
    0.07
     wifi
    0.07
    ){↵
    0.07
    __":↵
    0.07
    SetActive
    0.07
    !!!!↵↵
    0.07
    sealed
    0.07
     personalize
    0.07
     overwrite
    0.06
    Act Density 0.078%

    No Known Activations