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

    Neuronpedia

    INDEX
    Explanations

    comprehensive guide for life

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Acres
    0.45
     conflicto
    0.45
     Faces
    0.45
     Neces
    0.45
     Acts
    0.44
     Disabilities
    0.44
     Builds
    0.44
     Acuerdo
    0.42
     Actors
    0.42
    de
    0.41
    POSITIVE LOGITS
     cỡ
    0.50
     quantized
    0.48
     humming
    0.48
     stride
    0.47
     breadth
    0.47
     markedly
    0.47
    кових
    0.47
     routinely
    0.46
     calibrated
    0.45
     ஆகியவற்ற
    0.45
    Act Density 0.001%

    No Known Activations