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

    Neuronpedia

    INDEX
    Explanations

    words related to being basic or not complex

    oai_token-act-pair · gemini-2.0-flash

    simple

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     raiſ
    -1.03
    intenance
    -0.99
    مراجع
    -0.97
     itſelf
    -0.94
    مصادر
    -0.94
    LEncoder
    -0.92
     fhew
    -0.90
    ableness
    -0.88
    yship
    -0.86
    drawal
    -0.86
    POSITIVE LOGITS
     chré
    0.69
     financières
    0.64
     anciennes
    0.64
     prochaines
    0.63
     arbres
    0.63
     modernas
    0.61
     industriels
    0.61
     supérieures
    0.61
     démocr
    0.60
     pères
    0.60
    Act Density 1.271%

    No Known Activations