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

    Neuronpedia

    INDEX
    Explanations

    nested mathematical or programming expressions with parentheses and similar syntax

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

    function arguments or code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IsMutable
    -0.42
     betweenstory
    -0.38
    sizeCache
    -0.36
     zufolge
    -0.33
     gyhoeddwyd
    -0.32
     concess
    -0.32
    IALES
    -0.31
     оригіналу
    -0.31
     plates
    -0.31
    migrationBuilder
    -0.31
    POSITIVE LOGITS
    endcsname
    0.56
    WriteBarrier
    0.53
     Inſ
    0.52
    setArguments
    0.51
    MergeFrom
    0.50
    ResumeLayout
    0.50
    ViewImports
    0.50
    AddWithValue
    0.49
    лтемелер
    0.49
    IUrlHelper
    0.48
    Act Density 0.666%

    No Known Activations