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

    Neuronpedia

    INDEX
    Explanations

    image size and scaling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     handwriting
    0.43
     typographic
    0.41
     writing
    0.40
     practicable
    0.40
    字体
    0.40
     práct
    0.40
    㡀
    0.40
    লিখ
    0.40
    ົນ
    0.39
     społ
    0.39
    POSITIVE LOGITS
     scale
    0.45
     svom
    0.42
    Scale
    0.40
     skala
    0.40
    scale
    0.40
     scaling
    0.39
     масшта
    0.39
     Scaling
    0.39
    Scaling
    0.39
     scales
    0.38
    Act Density 0.164%

    No Known Activations