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

    Neuronpedia

    INDEX
    Explanations

    beginning, middle, end

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    binomial
    0.40
    monthly
    0.40
    interval
    0.38
    rpc
    0.38
    ըն
    0.38
    distribution
    0.38
    universal
    0.38
    neighbor
    0.38
    module
    0.37
    neq
    0.37
    POSITIVE LOGITS
     STYLE
    0.43
     COLLEGE
    0.43
     REFERENCES
    0.43
     References
    0.41
    OSPH
    0.40
     INNER
    0.39
    ENSATION
    0.39
     CLASS
    0.39
    ยาย
    0.39
     busc
    0.39
    Act Density 0.000%

    No Known Activations