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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ά
    -0.07
     رئيس
    -0.07
    頭
    -0.07
    主编
    -0.07
    /St
    -0.07
    localhost
    -0.07
    �
    -0.07
     maneuver
    -0.07
     color
    -0.06
    ภาพยน
    -0.06
    POSITIVE LOGITS
     nhắn
    0.08
    泄露
    0.07
    احتم
    0.07
    кли
    0.07
    罅
    0.07
    因为
    0.07
    (register
    0.06
     khuẩn
    0.06
    posite
    0.06
     contentValues
    0.06
    Act Density 0.009%

    No Known Activations