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

    Neuronpedia

    INDEX
    Explanations

    fill

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    楶
    0.42
    Jimmy
    0.41
     systematics
    0.40
    ಳಿತ
    0.40
     রিপ
    0.39
    rimidine
    0.39
    卽
    0.39
     जॉन
    0.38
    Dims
    0.38
    껴
    0.38
    POSITIVE LOGITS
     fill
    0.55
    FILL
    0.55
     filling
    0.55
     fills
    0.54
     FILL
    0.53
    fill
    0.52
    filling
    0.51
     filled
    0.50
    fills
    0.48
     might
    0.48
    Act Density 0.000%

    No Known Activations