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

    Neuronpedia

    INDEX
    Explanations

    definitions of terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     these
    0.46
    这种
    0.45
     estos
    0.44
     такие
    0.44
    等は
    0.42
     this
    0.42
    these
    0.41
    这些
    0.41
     seront
    0.40
    लेक्ट
    0.40
    POSITIVE LOGITS
     consisting
    0.55
     invented
    0.52
    that
    0.49
     چې
    0.48
     characterized
    0.46
     generalmente
    0.44
     That
    0.44
     commonly
    0.44
     terdiri
    0.43
     patented
    0.43
    Act Density 0.029%

    No Known Activations