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

    Neuronpedia

    INDEX
    Explanations

    elements of structured data, particularly in the context of documentation or programming syntax

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

    section identifiers with numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bewußt
    -0.53
    labelledby
    -0.52
    󠁢
    -0.48
    itinéraire
    -0.47
    cessite
    -0.45
    MessageTagHelper
    -0.43
     määrä
    -0.43
     wireType
    -0.42
     وتسجيلات
    -0.41
     Simplemente
    -0.41
    POSITIVE LOGITS
    ########.
    0.47
    PE
    0.40
     Vel
    0.40
    ніципалі
    0.39
     Loss
    0.38
     Helps
    0.38
    opa
    0.38
    <bos>
    0.38
     betweenstory
    0.37
     Y
    0.37
    Act Density 0.338%

    No Known Activations