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

    Neuronpedia

    INDEX
    Explanations

    references to contemporary standards or practices

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

    modern applications and fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tease
    -0.50
    奚
    -0.48
     Dice
    -0.46
    illage
    -0.46
    Apakah
    -0.46
    Clic
    -0.46
    retum
    -0.46
     Kies
    -0.46
    اخ
    -0.45
     ananas
    -0.45
    POSITIVE LOGITS
     modern
    2.06
    modern
    1.97
    Modern
    1.81
     Modern
    1.77
     MODERN
    1.70
    MODERN
    1.63
     modernes
    1.60
     modernas
    1.56
     moderne
    1.52
     moderno
    1.52
    Act Density 0.006%

    No Known Activations