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

    Neuronpedia

    INDEX
    Explanations

    this is a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Además
    0.44
    ﺮ
    0.41
     Jehová
    0.41
     daí
    0.40
     mencionar
    0.39
    رآ
    0.39
     máme
    0.38
    便是
    0.38
     cantidades
    0.38
    も含
    0.38
    POSITIVE LOGITS
     NOT
    0.43
     server
    0.43
     Dit
    0.43
     rising
    0.42
    fik
    0.42
     kai
    0.42
     bug
    0.42
     Generator
    0.42
     aspirated
    0.42
     blo
    0.41
    Act Density 0.006%

    No Known Activations