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

    Neuronpedia

    INDEX
    Explanations

    phrases and questions related to definitions and meanings of terms

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

    non-alphanumeric and short words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.48
     endwhile
    -0.45
     metav
    -0.42
     iprot
    -0.41
     MenuView
    -0.41
    enterOuterAlt
    -0.40
    wapV
    -0.40
    devise
    -0.40
    دانشنامهٔ
    -0.40
    فایل‌لار
    -0.39
    POSITIVE LOGITS
     Islands
    0.43
     arbejds
    0.43
    vician
    0.42
    RenderAtEndOf
    0.39
     plads
    0.38
    ādā
    0.38
    crata
    0.38
     eiland
    0.38
    minal
    0.38
     læng
    0.38
    Act Density 0.075%

    No Known Activations