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

    Neuronpedia

    INDEX
    Explanations

    drawing, sketch, create

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     proteomics
    0.41
     écrit
    0.41
     escrit
    0.41
     escrita
    0.41
     Written
    0.41
     تكتب
    0.40
     لکھا
    0.39
     Schreiben
    0.38
    rift
    0.38
     yazı
    0.38
    POSITIVE LOGITS
    sketch
    0.77
     sketch
    0.75
    Sketch
    0.73
     sketched
    0.73
     sketches
    0.72
     sketching
    0.71
     Sketch
    0.67
    hand
    0.60
     Sketches
    0.60
     hand
    0.59
    Act Density 0.207%

    No Known Activations