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

    Neuronpedia

    INDEX
    Explanations

    related terms and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nltk
    0.73
     "
    0.70
    Alternatively
    0.69
    Trusted
    0.68
    such
    0.67
    relatively
    0.67
    the
    0.65
    0.61
     **
    0.60
     `
    0.59
    POSITIVE LOGITS
    ™,
    1.28
    ™.
    1.21
     Syndrome
    1.21
    izadores
    1.18
    と呼ばれる
    1.18
    ™
    1.17
     capables
    1.14
     எனப்படும்
    1.14
     라는
    1.14
     Productions
    1.13
    Act Density 0.777%

    No Known Activations