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

    Neuronpedia

    INDEX
    Explanations

    importing python libraries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     попасть
    0.35
     विकलांग
    0.34
    🏊
    0.31
    álov
    0.29
    罾
    0.29
    assanam
    0.29
    ätzung
    0.28
    嵬
    0.28
    avatt
    0.28
     эмне
    0.28
    POSITIVE LOGITS
     matplotlib
    0.45
     itertools
    0.39
     pandas
    0.38
     numpy
    0.37
     C
    0.35
     tensorflow
    0.34
    iostream
    0.33
     datetime
    0.32
     math
    0.31
     tools
    0.31
    Act Density 0.090%

    No Known Activations