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

    Neuronpedia

    INDEX
    Explanations

    RFC numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    لق
    -0.08
    าง
    -0.07
     r
    -0.07
     articulated
    -0.07
    ��
    -0.07
     diret
    -0.06
     Luz
    -0.06
    Helper
    -0.06
     вп
    -0.06
    达到
    -0.06
    POSITIVE LOGITS
    险
    0.07
    енні
    0.07
     formatDate
    0.07
    panel
    0.06
    軽
    0.06
     analy
    0.06
     Phân
    0.06
     isEnabled
    0.06
    ugging
    0.06
     rekl
    0.06
    Act Density 0.002%

    No Known Activations