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

    Neuronpedia

    INDEX
    Explanations

    specific numerical data and statistics presented in a structured format

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

    Code or numerical data snippets

    np_acts-logits-general · gemini-2.0-flash

    :o2 transition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    numerusform
    -0.75
    InstrumentedTest
    -0.74
    </i>
    -0.71
     محفوظة
    -0.69
    تقاوى
    -0.67
    AnimationsModule
    -0.67
    GraphicsUnit
    -0.65
    AndEndTag
    -0.63
    Aktualisiert
    -0.61
     EnglishChoose
    -0.61
    POSITIVE LOGITS
     …
    0.78
    AddTagHelper
    0.71
     […]
    0.69
    Personensuche
    0.67
     [...]
    0.60
    ItemBackground
    0.59
    millimeters
    0.57
     ..."
    0.56
     kohdetta
    0.56
     ...
    0.55
    Act Density 2.631%

    No Known Activations