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

    Neuronpedia

    INDEX
    Explanations

    drawing shapes and objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     assurer
    0.38
     ningún
    0.36
     zapewnia
    0.36
     unamb
    0.35
     crisi
    0.35
     être
    0.35
     pursuant
    0.34
     adversity
    0.34
     vermeiden
    0.34
     distrust
    0.33
    POSITIVE LOGITS
     tulip
    0.32
     whirl
    0.31
    篦
    0.30
    Tul
    0.30
     फिल्मी
    0.30
    paintbrush
    0.30
    OGLE
    0.30
    sels
    0.30
    旋转
    0.29
    arded
    0.28
    Act Density 0.117%

    No Known Activations