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

    Neuronpedia

    INDEX
    Explanations

    common phrases and commands relevant to instructions and processes

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

    proof an update

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⓧ
    -0.43
     Италијани
    -0.38
    ViewImports
    -0.36
    ➯
    -0.35
     resourceCulture
    -0.32
    Hentet
    -0.31
    SerializedSize
    -0.31
    ContentAlignment
    -0.31
    secta
    -0.31
    PYX
    -0.29
    POSITIVE LOGITS
    Cyfeiriadau
    0.68
     tartalomajánló
    0.58
    tagHelperRunner
    0.56
    ſchaft
    0.56
     Wikimedijinoj
    0.55
    iſen
    0.53
    ロウィン
    0.53
    GEBUR
    0.52
    inaison
    0.52
     queſto
    0.52
    Act Density 0.003%

    No Known Activations