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

    Neuronpedia

    INDEX
    Explanations

    initialisms and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    呤
    0.72
    ামিটার
    0.69
    தல்
    0.68
    трите
    0.68
     fistule
    0.67
    consistent
    0.67
    ImageQueue
    0.67
    उने
    0.66
     inverses
    0.66
    irectional
    0.66
    POSITIVE LOGITS
     Harvard
    0.77
     Planning
    0.75
    rc
    0.74
     pr
    0.73
     Jobs
    0.73
    MRC
    0.71
    PRA
    0.69
     Foundation
    0.68
    STEP
    0.68
    Dear
    0.67
    Act Density 0.169%

    No Known Activations