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

    Neuronpedia

    INDEX
    Explanations

    character sequences that resemble numerical or code-like formats

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

    Text enclosed in "quotes/special characters"

    np_acts-logits-general · gemini-2.0-flash

    quoted text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SharedDtor
    -1.02
    SharedCtor
    -0.99
     <>",
    -0.97
    InjectAttribute
    -0.92
    UrlResolution
    -0.91
     Италијани
    -0.90
     PyLong
    -0.90
     '\\;'
    -0.90
     mergeFrom
    -0.90
    oredCriteria
    -0.88
    POSITIVE LOGITS
    Bạn
    0.44
     holding
    0.44
    “
    0.43
    c
    0.42
    ’
    0.42
     “
    0.41
    ״
    0.40
    Holding
    0.39
    caten
    0.39
     Last
    0.39
    Act Density 0.081%

    No Known Activations