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

    Neuronpedia

    INDEX
    Explanations

    code definition and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nikov
    0.28
    नेल
    0.28
    akor
    0.27
    erek
    0.27
    நுட்ப
    0.26
     sér
    0.26
     correspondió
    0.26
     भारतातील
    0.26
    antiene
    0.25
     geschikt
    0.25
    POSITIVE LOGITS
    __
    0.33
    Impl
    0.33
     എന്ന
    0.32
    Helper
    0.31
    ::
    0.29
    Module
    0.29
    ๊
    0.29
    类
    0.28
    ()
    0.27
    Ctrl
    0.27
    Act Density 0.023%

    No Known Activations