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

    Neuronpedia

    INDEX
    Explanations

    structured programming syntax and patterns

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

    code and non-english words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ChildScrollView
    -0.49
    发表于
    -0.48
     MessageBoxIcon
    -0.48
    apimachinery
    -0.47
    +#+
    -0.46
    @[+][
    -0.45
     onCreateView
    -0.43
    EndInit
    -0.43
    EndContext
    -0.42
     الحره
    -0.42
    POSITIVE LOGITS
     المعيارى
    0.66
    UnusedPrivate
    0.47
    moth
    0.43
     展板
    0.42
    tanleria
    0.42
    ьаж
    0.42
    eira
    0.40
    putable
    0.40
    ilhas
    0.39
    cyklopedia
    0.39
    Act Density 0.002%

    No Known Activations