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

    Neuronpedia

    INDEX
    Explanations

    structures in programming code, particularly control structures and statements

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

    code snippets with user context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     상세
    -0.40
     radi
    -0.35
     hik
    -0.34
     pe
    -0.32
     mam
    -0.32
     rece
    -0.31
    beforeSend
    -0.31
    insertBefore
    -0.30
     cer
    -0.30
     esp
    -0.30
    POSITIVE LOGITS
    ftagPool
    0.81
    IntoConstraints
    0.72
     CreateTagHelper
    0.71
    Personensuche
    0.64
    wiſe
    0.62
    sizeCache
    0.60
     desmotivaciones
    0.60
     Verbreitung
    0.60
     myſelf
    0.58
    InjectAttribute
    0.58
    Act Density 0.031%

    No Known Activations