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

    Neuronpedia

    INDEX
    Explanations

    fill color

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     координат
    0.38
     Стар
    0.38
    tgts
    0.38
     जानकर
    0.37
    Euph
    0.37
    待
    0.37
    沸
    0.36
    logn
    0.36
    tempCard
    0.36
     Euph
    0.36
    POSITIVE LOGITS
     fill
    1.43
     filling
    1.36
     Fill
    1.32
    fill
    1.27
    Fill
    1.27
     fills
    1.24
     Filling
    1.24
     fillColor
    1.23
     FILL
    1.19
     fillings
    1.17
    Act Density 0.030%

    No Known Activations