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

    Neuronpedia

    INDEX
    Explanations

    references to users and programming-related syntax

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

    LaTeX spacing commands (hspace, phantom)

    np_acts-logits-general · gemini-2.0-flash

    LaTeX spacing commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fjspx
    -0.66
     Cap
    -0.58
     azar
    -0.58
    <eos>
    -0.57
    ↵↵↵
    -0.50
    ciaż
    -0.49
    вес
    -0.48
    itemView
    -0.48
     olimp
    -0.48
    langen
    -0.47
    POSITIVE LOGITS
    multicolumn
    2.88
    multirow
    1.70
    HtmlAttribute
    1.08
    存于互联网档案馆
    1.05
    ſelves
    1.02
     nahilalakip
    1.02
    IsContent
    1.01
    \{\\
    0.99
    ConstraintMaker
    0.96
     propOrder
    0.95
    Act Density 0.008%

    No Known Activations