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

    Neuronpedia

    INDEX
    Explanations

    journal citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     অজ্ঞাত
    0.77
    瀨
    0.77
     이런
    0.75
    地元
    0.73
     newline
    0.71
     saliva
    0.71
     점점
    0.70
     avoiding
    0.70
     coeficiente
    0.69
    逐渐
    0.69
    POSITIVE LOGITS
     Supplement
    1.44
    Supplement
    1.43
     Suppl
    1.36
    Issue
    1.28
    Suppl
    1.25
     supplement
    1.25
    issue
    1.24
     Issue
    1.24
    supplement
    1.22
     Supplements
    1.19
    Act Density 0.026%

    No Known Activations