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

    Neuronpedia

    INDEX
    Explanations

    programming code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    obedience
    0.45
    由
    0.45
     obedience
    0.44
     forza
    0.42
    steady
    0.41
     Ti
    0.41
     Nummer
    0.40
    దయ
    0.40
    त
    0.39
     cuánt
    0.39
    POSITIVE LOGITS
     ಮಾಡಲು
    0.46
    macd
    0.41
     actinides
    0.41
    anners
    0.40
     ၊
    0.40
    槃
    0.40
     kijken
    0.40
     вересня
    0.39
    |.
    0.39
    älter
    0.39
    Act Density 0.005%

    No Known Activations