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

    Neuronpedia

    INDEX
    Explanations

    mentions of data blocks and block-related terms in technical contexts

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

    block or blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     getItemId
    -0.48
    Referències
    -0.44
    DotNetBar
    -0.44
    OGND
    -0.43
    DIPSETTING
    -0.42
    Espèce
    -0.41
    讐
    -0.40
    TokenNameDOT
    -0.40
    󠁮
    -0.39
    addGap
    -0.39
    POSITIVE LOGITS
     block
    1.95
     Block
    1.79
    block
    1.77
    Block
    1.75
     BLOCK
    1.72
     blocks
    1.67
     Blocks
    1.59
    BLOCK
    1.58
    blocks
    1.51
     blok
    1.51
    Act Density 0.029%

    No Known Activations