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

    Neuronpedia

    INDEX
    Explanations

    terms and concepts related to algorithms, techniques, and strategies

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

    methods and strategies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Infórmanos
    -0.65
    LookAnd
    -0.64
    msgTypes
    -0.63
     useAppContext
    -0.63
    enumii
    -0.55
    enumi
    -0.54
     "..\..\..\
    -0.52
     *++
    -0.50
    HasIndex
    -0.50
    FormTagHelper
    -0.50
    POSITIVE LOGITS
    脚注の使い方
    0.40
     Dall
    0.35
     GlobalKey
    0.35
    ISupport
    0.34
    isielt
    0.33
    /**
    0.33
    eseorang
    0.31
     Informasi
    0.30
    Individual
    0.29
     Verify
    0.29
    Act Density 0.453%

    No Known Activations