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

    Neuronpedia

    INDEX
    Explanations

    convex

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SERVICE
    -0.07
    tahun
    -0.06
     Julian
    -0.06
    permanent
    -0.06
    liga
    -0.06
    世
    -0.06
    beat
    -0.06
     aspiring
    -0.06
     هدف
    -0.06
     розрах
    -0.06
    POSITIVE LOGITS
     convex
    0.07
     `
    0.07
     gerçekleştir
    0.07
     یک
    0.07
     подк
    0.06
    회
    0.06
     μικ
    0.06
     PriorityQueue
    0.06
    .symmetric
    0.06
     profession
    0.06
    Act Density 0.001%

    No Known Activations