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

    Neuronpedia

    INDEX
    Explanations

    references to programming blocks or constructs in code

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

    block context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.52
     Roskov
    -0.50
    gypti
    -0.49
     Expectations
    -0.48
    apsed
    -0.47
    dud
    -0.47
    Advantage
    -0.46
     PSP
    -0.46
    unisex
    -0.46
    dibles
    -0.46
    POSITIVE LOGITS
    Block
    2.25
     Block
    2.13
     BLOCK
    1.44
    BLOCK
    1.21
     Blocks
    1.07
    getBlock
    1.05
     block
    1.05
    Blocks
    1.02
     ブロック
    1.02
     Blok
    0.95
    Act Density 0.004%

    No Known Activations