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

    Neuronpedia

    INDEX
    Explanations

    which

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     artık
    -0.07
     đọ
    -0.06
    AlertDialog
    -0.06
     Тому
    -0.06
    Production
    -0.06
     sabe
    -0.06
     Lag
    -0.06
    ない
    -0.06
     Panc
    -0.06
    终于
    -0.06
    POSITIVE LOGITS
     Rarity
    0.08
     Founder
    0.07
     OutputStream
    0.06
     acknowled
    0.06
    /****************************************************************
    0.06
     Swarm
    0.06
     Rai
    0.06
     instruments
    0.06
    овый
    0.06
    _ns
    0.06
    Act Density 0.000%

    No Known Activations