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

    Neuronpedia

    INDEX
    Explanations

    hugging face models on urls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     presentan
    0.46
     Brexit
    0.44
    நடிக
    0.44
     ".")
    0.43
    赞
    0.42
     Ги
    0.41
     Naam
    0.41
    GLASS
    0.41
     Burb
    0.41
    🐯
    0.41
    POSITIVE LOGITS
    Databaze
    0.40
     большого
    0.39
     ਵੱ
    0.39
     αριθ
    0.38
    Okay
    0.38
     आद
    0.38
     skirts
    0.37
     effectu
    0.37
    র্য
    0.37
    qty
    0.37
    Act Density 0.000%

    No Known Activations