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

    Neuronpedia

    INDEX
    Explanations

    numerical values and identifiers in a structured format

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

    numbers and separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     followed
    -0.42
     in
    -0.39
     is
    -0.37
     for
    -0.36
     and
    -0.34
     as
    -0.34
     inc
    -0.34
     indeed
    -0.34
     listed
    -0.33
     mitään
    -0.33
    POSITIVE LOGITS
    Autoritní
    0.66
     виправивши
    0.65
    참고
    0.61
     initComponents
    0.60
    uxxxx
    0.59
     صوتيه
    0.58
    Personendaten
    0.58
    KommentareTeilen
    0.58
     snippetHide
    0.56
    tvguidetime
    0.55
    Act Density 0.123%

    No Known Activations