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

    Neuronpedia

    INDEX
    Explanations

    references to various forms of support provided

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

    providing support for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    立
    -0.40
     guard
    -0.38
    cry
    -0.36
    vő
    -0.34
    DataAnnotations
    -0.34
    рь
    -0.34
     veux
    -0.33
     inf
    -0.33
    baris
    -0.33
    UrlResolution
    -0.33
    POSITIVE LOGITS
     kasarigan
    0.58
    TagMode
    0.55
     ब्रेकडाउन
    0.49
    RUnlock
    0.48
    WriteBarrier
    0.48
    ScopeManager
    0.48
    TemporalType
    0.47
    titleMargin
    0.47
    Geplaatst
    0.46
     nakalista
    0.45
    Act Density 0.031%

    No Known Activations