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

    Neuronpedia

    INDEX
    Explanations

    `import` statement `from` module

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    !')
    0.37
    Implemented
    0.36
    ertel
    0.36
    ванием
    0.36
    是谁
    0.36
    ndarray
    0.35
     خارجی
    0.35
    ्रम
    0.35
    َی
    0.35
    рованием
    0.35
    POSITIVE LOGITS
    (".");
    0.42
    ="@
    0.41
    ,"@
    0.40
    ㅝ
    0.39
     helpers
    0.39
     Helpers
    0.38
     @
    0.38
     Med
    0.38
    ＠
    0.38
     "@
    0.38
    Act Density 0.002%

    No Known Activations