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

    Neuronpedia

    INDEX
    Explanations

    numerical data and mathematical expressions

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

    Numbers followed by ".\ref" or "]"

    np_acts-logits-general · gemini-2.0-flash

    references and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '){
    -0.77
    "){
    -0.73
    '))
    -0.71
    yntaxException
    -0.70
    ":
    -0.69
    '),
    -0.69
    "):
    -0.68
    niczy
    -0.67
    noinspection
    -0.67
     يتيمه
    -0.67
    POSITIVE LOGITS
    0
    1.17
    5
    1.06
    9
    1.03
    8
    1.03
    6
    1.02
    3
    0.99
    4
    0.99
    7
    0.98
    2
    0.97
    1
    0.89
    Act Density 3.471%

    No Known Activations