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

    Neuronpedia

    INDEX
    Explanations

    syntax patterns commonly used in regular expressions

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

    Text enclosed in brackets or parentheses

    np_acts-logits-general · gemini-2.0-flash

    special characters like brackets and braces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ワイイ
    -0.58
    @@@@@@@@
    -0.57
    raisemb
    -0.54
    interopRequire
    -0.53
     themselves
    -0.51
     itſelf
    -0.51
     herself
    -0.50
     itself
    -0.49
     Digit
    -0.49
    nestjs
    -0.49
    POSITIVE LOGITS
    0.75
    脚注の使い方
    0.66
    awtextra
    0.65
     propOrder
    0.63
     <>",
    0.62
     Roskov
    0.61
    mapStateToProps
    0.58
    ArgsConstructor
    0.56
    TryParse
    0.55
    ंदीखरीदारी
    0.53
    Act Density 0.707%

    No Known Activations