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

    Neuronpedia

    INDEX
    Explanations

    math and science education

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     odv
    0.39
     Ud
    0.38
     vagu
    0.38
     ethical
    0.38
    Tou
    0.37
     neuroscience
    0.36
     coqu
    0.36
     pir
    0.35
    Busy
    0.35
     satisfying
    0.34
    POSITIVE LOGITS
    㳚
    0.47
    idency
    0.42
    裔
    0.41
    indruck
    0.40
     Atoms
    0.40
    衵
    0.40
     আরো
    0.39
    ష్ట
    0.39
     Proficiency
    0.39
    iments
    0.38
    Act Density 0.006%

    No Known Activations