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

    Neuronpedia

    INDEX
    Explanations

    occurrences of whitespace or empty characters

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

    numbers followed by period

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.65
    évaluateur
    -0.59
    IContainer
    -0.59
     שוליים
    -0.58
     cherchés
    -0.54
    ThroughAttribute
    -0.53
     Roskov
    -0.52
     Grüßen
    -0.50
     ส์
    -0.49
     незавершена
    -0.48
    POSITIVE LOGITS
     Scho
    0.54
     Phen
    0.48
     Ph
    0.46
    Dek
    0.44
     flav
    0.44
    Rik
    0.43
     newArr
    0.43
    Bla
    0.43
    putnik
    0.42
     FontWeight
    0.41
    Act Density 0.059%

    No Known Activations