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

    Neuronpedia

    INDEX
    Explanations

    occurrences of a specific numeric or versioning format

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

    `<start_of_turn>user`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     desmotivaciones
    -0.59
    NamedQueries
    -0.54
    ьажоргаш
    -0.53
     wikipagina
    -0.52
     Inscrivez
    -0.49
    -0.49
    colgante
    -0.49
     increí
    -0.48
    CloseOperation
    -0.47
     masukan
    -0.47
    POSITIVE LOGITS
    -
    0.53
     nakalista
    0.45
    Билгалдахарш
    0.43
     CreateTagHelper
    0.42
    比特派
    0.42
    AndEndTag
    0.41
    -%
    0.40
    {~
    0.40
    ="-
    0.39
    ("/:
    0.39
    Act Density 0.000%

    No Known Activations