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

    Neuronpedia

    INDEX
    Explanations

    broccoli and master node

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     btw
    0.51
    Montreal
    0.45
    femin
    0.42
     WA
    0.42
     BTW
    0.42
     WT
    0.41
    ↵
    0.41
     indol
    0.41
    CANADA
    0.41
     Archipelago
    0.41
    POSITIVE LOGITS
    یت
    0.46
    ༣
    0.44
    ейчас
    0.43
     pouco
    0.42
    Telefono
    0.42
    㗁
    0.42
     мало
    0.42
    σια
    0.42
    éticos
    0.41
     باتیں
    0.41
    Act Density 0.007%

    No Known Activations