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

    Neuronpedia

    INDEX
    Explanations

    negative or diminishing values associated with data or observations

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

    citations like [@number]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    الإنجليزية
    -0.71
     '\\;'
    -0.69
     AssemblyCulture
    -0.67
     opérés
    -0.65
    webElement
    -0.63
     autorytatywna
    -0.60
    OGND
    -0.60
    SequentialGroup
    -0.59
     EconPapers
    -0.58
    InjectAttribute
    -0.56
    POSITIVE LOGITS
    9
    0.45
    3
    0.42
    4
    0.42
    2
    0.42
    6
    0.42
    8
    0.42
    5
    0.42
    1
    0.41
    7
    0.40
    Later
    0.34
    Act Density 0.007%

    No Known Activations