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

    Neuronpedia

    INDEX
    Explanations

    innate desire for meaning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     an
    0.45
    전
    0.45
    相关的
    0.44
    r
    0.44
    2
    0.43
    said
    0.42
    If
    0.42
    The
    0.41
    ني
    0.41
    zu
    0.41
    POSITIVE LOGITS
     own
    1.05
     Own
    0.72
     ability
    0.67
     innate
    0.61
     OWN
    0.59
     собственные
    0.58
    own
    0.57
     inability
    0.54
     disruptive
    0.52
     innovative
    0.52
    Act Density 0.008%

    No Known Activations