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

    Neuronpedia

    INDEX
    Explanations

    academic fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     barking
    0.75
     ค่า
    0.71
     raggiungere
    0.71
     skipping
    0.71
     withhold
    0.71
     destroyed
    0.68
     sleeveless
    0.68
    imated
    0.66
     stifle
    0.64
     Kidd
    0.64
    POSITIVE LOGITS
     psychology
    2.19
     sociology
    2.13
     Psychology
    2.09
     Sociology
    2.02
     neuroscience
    2.00
     linguistics
    1.91
     anthropology
    1.90
    Economics
    1.87
     Economics
    1.83
     economics
    1.83
    Act Density 0.723%

    No Known Activations