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

    Neuronpedia

    INDEX
    Explanations

    Frame

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     paragraphs
    -0.07
    onds
    -0.06
     welfare
    -0.06
    ibre
    -0.06
    建设
    -0.06
     Παν
    -0.06
     Advisors
    -0.06
     الأم
    -0.06
     analogous
    -0.06
    Observable
    -0.06
    POSITIVE LOGITS
     crashing
    0.07
    otech
    0.06
    :i
    0.06
     vás
    0.06
    ilian
    0.06
    vinfos
    0.06
     sạn
    0.06
     Too
    0.06
    hawks
    0.06
    .userId
    0.06
    Act Density 0.004%

    No Known Activations