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

    Neuronpedia

    INDEX
    Explanations

    occurrences of periods that may indicate sentence endings in code or comments

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

    .hpp, .h, .php, .lua file extensions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AnchorStyles
    -0.73
    脚注の使い方
    -0.67
    protoimpl
    -0.66
    httphttps
    -0.64
    tagHelperRunner
    -0.63
    leneck
    -0.60
    Cyfarwyddwr
    -0.60
    chengladbach
    -0.59
    DockStyle
    -0.59
     ſever
    -0.58
    POSITIVE LOGITS
    IUrlHelper
    0.47
    .
    0.43
    ?.
    0.40
    ™.
    0.40
    fromnode
    0.39
     dilan
    0.38
     is
    0.37
    |.
    0.35
    bio
    0.35
    *.
    0.35
    Act Density 0.053%

    No Known Activations