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

    Neuronpedia

    INDEX
    Explanations

    elements representing mathematical or programming syntax

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

    Followed by the letter 'b'

    np_acts-logits-general · gemini-2.0-flash

    a, b, c, or d

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Хьажоргаш
    -0.66
     Wikimedijinoj
    -0.64
    reportWebVitals
    -0.59
    GrantedAuthority
    -0.58
     Савезне
    -0.56
     odkazy
    -0.56
     HttpHeaders
    -0.55
    fromnode
    -0.55
     jadx
    -0.54
    Vidite
    -0.54
    POSITIVE LOGITS
     b
    0.99
    b
    0.85
     B
    0.82
    B
    0.69
     getB
    0.66
     ویکی‌پدیای
    0.66
    ｂ
    0.64
     A
    0.61
    getB
    0.58
    ب
    0.52
    Act Density 0.375%

    No Known Activations