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

    Neuronpedia

    INDEX
    Explanations

    occurrences of hash symbols and formatted text in code

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

    code references with #

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    -0.36
     unfortunately
    -0.32
     ponieważ
    -0.32
    .
    -0.32
     ведь
    -0.31
    ing
    -0.31
    ming
    -0.31
     pratique
    -0.31
     because
    -0.31
    as
    -0.31
    POSITIVE LOGITS
    MigrationBuilder
    0.89
    rungsseite
    0.88
     StringTokenizer
    0.76
    ंदीखरीदारी
    0.76
     kasarigan
    0.75
     $#
    0.72
    WriteTagHelper
    0.72
     autorytatywna
    0.71
    principalColumn
    0.71
     للاسماء
    0.70
    Act Density 0.054%

    No Known Activations