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

    Neuronpedia

    INDEX
    Explanations

    namespace

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     添加
    -0.07
    Und
    -0.07
    _on
    -0.07
    iltro
    -0.07
    HEN
    -0.07
     MAT
    -0.07
    	connection
    -0.06
    HUD
    -0.06
    _LAYER
    -0.06
     repaired
    -0.06
    POSITIVE LOGITS
    ня
    0.06
     Horizontal
    0.06
    -sup
    0.06
    Scalars
    0.06
    官网
    0.06
     использ
    0.06
    baum
    0.06
    741
    0.06
     Dysfunction
    0.06
    ��取
    0.06
    Act Density 0.001%

    No Known Activations