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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions involving arrays or matrices

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

    Math mode environments with matrix-like structures

    np_acts-logits-general · gemini-2.0-flash

    matrix and array notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    verifyException
    -0.65
     tartalomajánló
    -0.64
    offsetof
    -0.63
    principalTable
    -0.62
    ConfigureAwait
    -0.61
    endpush
    -0.61
    tonsoft
    -0.61
     termica
    -0.60
     ģ
    -0.60
     magique
    -0.59
    POSITIVE LOGITS
    出版年
    0.63
    importe
    0.54
     colspan
    0.53
     rowspan
    0.51
    kunta
    0.50
    Brains
    0.48
    enumii
    0.47
    onyms
    0.46
    CloseOperation
    0.46
    AddTagHelper
    0.46
    Act Density 0.022%

    No Known Activations