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

    Neuronpedia

    INDEX
    Explanations

    national helpline HELP

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    स्टम
    0.63
    osh
    0.59
    oster
    0.59
     désigne
    0.58
     ker
    0.58
    ErrMsg
    0.57
    (:,:,
    0.56
    ંપ
    0.56
     अध्यक्ष
    0.56
     Life
    0.56
    POSITIVE LOGITS
    nati
    0.72
     PN
    0.64
    saturated
    0.63
    ഗ്യ
    0.62
    aturated
    0.62
    rato
    0.61
    nsp
    0.60
     meals
    0.60
    ষে
    0.58
    synthetic
    0.58
    Act Density 0.071%

    No Known Activations