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

    Neuronpedia

    INDEX
    Explanations

    phrases referencing large quantities

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

    number of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ientras
    -0.66
     autorytatywna
    -0.57
    arangay
    -0.56
    بوابة
    -0.56
    verwijspagina
    -0.54
    GEBURTSDATUM
    -0.54
    Autoritní
    -0.52
     tartalomajánló
    -0.52
    ambién
    -0.50
     مرئيه
    -0.49
    POSITIVE LOGITS
     Vielzahl
    0.65
    Few
    0.61
     few
    0.61
    MANY
    0.60
     many
    0.60
     dozens
    0.58
    多くの
    0.58
    多数
    0.57
    many
    0.57
     Few
    0.57
    Act Density 0.030%

    No Known Activations