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

    Neuronpedia

    INDEX
    Explanations

    World Heritage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     seems
    0.43
     ARN
    0.41
     $
    0.41
     Salvatore
    0.41
     seemed
    0.40
    拿着
    0.40
    이지만
    0.40
     ~$
    0.40
     NVIDIA
    0.40
     Measured
    0.40
    POSITIVE LOGITS
     suppress
    0.50
     preprocess
    0.48
     用户
    0.45
     unfairly
    0.44
     незакон
    0.43
     preachers
    0.42
    ouncy
    0.42
     sedentary
    0.42
    SpawnEntry
    0.42
     Jharkhand
    0.42
    Act Density 0.003%

    No Known Activations