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

    Neuronpedia

    INDEX
    Explanations

    statements or phrases indicating agreement with previous results or data

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

    agreement with consistency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NameInMap
    -0.59
    TagMode
    -0.49
     autorytatywna
    -0.46
    WithIOException
    -0.45
    $_['
    -0.44
     صوتيه
    -0.44
     怎样
    -0.43
    tudiant
    -0.42
     crystall
    -0.41
    Coordonnées
    -0.40
    POSITIVE LOGITS
     confirming
    0.52
     consistent
    0.47
    consistent
    0.46
    expected
    0.45
     expected
    0.45
     confirmed
    0.45
     indicating
    0.42
     vindicated
    0.42
     bestätigen
    0.42
     confirmer
    0.41
    Act Density 0.160%

    No Known Activations