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

    Neuronpedia

    INDEX
    Explanations

    instances of significant coding structure or elements in programming-related text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    code file names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WithMany
    -0.48
     怎样
    -0.46
    вић
    -0.44
    SaveChangesAsync
    -0.42
     useState
    -0.41
     mourut
    -0.41
     bParam
    -0.41
    dAtA
    -0.40
    ngOnInit
    -0.40
    useState
    -0.38
    POSITIVE LOGITS
     ***!
    0.54
    ⟬
    0.52
    帖最后由
    0.51
    Hochspringen
    0.49
     kasarigan
    0.47
    \{\\
    0.47
     يتيمه
    0.45
    matchCondition
    0.44
    脚注の使い方
    0.44
    tagHelper
    0.42
    Act Density 0.001%

    No Known Activations