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

    Neuronpedia

    INDEX
    Explanations

    +

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     الاس
    -0.08
    tes
    -0.06
    ربع
    -0.06
    emey
    -0.06
     ถ
    -0.06
     이번
    -0.06
     pageSize
    -0.06
     près
    -0.06
     vorhand
    -0.06
     Katherine
    -0.06
    POSITIVE LOGITS
    domains
    0.07
     [-
    0.07
    ��
    0.07
     Needs
    0.06
     pygame
    0.06
    cluster
    0.06
     +
    0.06
     concerts
    0.06
     音
    0.06
     ALWAYS
    0.06
    Act Density 0.004%

    No Known Activations