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

    Neuronpedia

    INDEX
    Explanations

    occurrences of numerical values or digit sequences in the text

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

    n followed by punctuation or newline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.64
    AddTagHelper
    -0.61
    AndEndTag
    -0.58
    testify
    -0.57
     CreateTagHelper
    -0.55
    -0.54
    Datuak
    -0.53
     propOrder
    -0.53
     Administrativna
    -0.52
    تقاوى
    -0.51
    POSITIVE LOGITS
    <bos>
    0.59
    \
    0.56
    ning
    0.48
    "
    0.48
    N
    0.47
    R
    0.44
    numerusform
    0.43
    }
    0.43
    n
    0.42
    )
    0.42
    Act Density 0.057%

    No Known Activations