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

    Neuronpedia

    INDEX
    Explanations

    the presence of newline characters in code snippets

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

    Characters preceding format specifiers

    np_acts-logits-general · gemini-2.0-flash

    code punctuation follows "n"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TagHelpers
    -0.57
    KELEY
    -0.53
    chooser
    -0.52
    enaire
    -0.52
    ParallelGroup
    -0.51
    ATORY
    -0.51
    IVOS
    -0.50
    =".$
    -0.50
     Савезне
    -0.50
    AILED
    -0.49
    POSITIVE LOGITS
     متعلقه
    0.73
     feminino
    0.66
    \
    0.66
     "..\..\..\
    0.65
     nakalista
    0.64
    seamnă
    0.63
     milo
    0.62
     itſelf
    0.61
    IsContent
    0.61
     محفوظة
    0.61
    Act Density 0.057%

    No Known Activations