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

    Neuronpedia

    INDEX
    Explanations

    conditional statements and concepts related to assumptions or requirements

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

    less harshly, ever find

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدی
    -0.53
    interopRequire
    -0.48
    GOTREF
    -0.48
    BeginInit
    -0.47
    providedIn
    -0.46
    SerializedSize
    -0.46
    WireFormatLite
    -0.45
    DoubleQuotes
    -0.42
    AndEndTag
    -0.42
    UserScript
    -0.41
    POSITIVE LOGITS
     thước
    0.51
    ⁩
    0.43
     zentralen
    0.41
    ⓘ
    0.41
    íncia
    0.41
     věci
    0.40
     city
    0.40
     **/
    0.40
     simple
    0.40
    package
    0.39
    Act Density 0.048%

    No Known Activations