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

    Neuronpedia

    INDEX
    Explanations

    Confidence intervals in academic studies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Yamaha
    -0.06
     reflective
    -0.06
    aro
    -0.06
    w
    -0.06
    شف
    -0.06
     schwer
    -0.06
    -bedroom
    -0.06
     上海
    -0.06
    America
    -0.06
    eç
    -0.06
    POSITIVE LOGITS
    ITER
    0.06
    ORIZONTAL
    0.06
     バ
    0.06
     invit
    0.06
     แล
    0.06
     Вони
    0.06
     GDPR
    0.06
     cort
    0.06
     přízn
    0.06
     Дон
    0.06
    Act Density 0.065%

    No Known Activations