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

    Neuronpedia

    INDEX
    Explanations

    using System; Collections Linq

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wedges
    0.40
     wedge
    0.39
    Arn
    0.39
    antlr
    0.39
    Xml
    0.38
    Again
    0.37
    CodeDom
    0.37
    Draw
    0.36
    кли
    0.36
     ガラス
    0.36
    POSITIVE LOGITS
     करती
    0.39
     NEET
    0.38
     PNP
    0.38
    RETURNTRANSFER
    0.38
     કરે
    0.38
     तब्
    0.37
     thể
    0.37
     체
    0.37
     instaur
    0.37
     orice
    0.37
    Act Density 0.000%

    No Known Activations