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

    Neuronpedia

    INDEX
    Explanations

    parentheses, equals signs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DVD
    -0.07
    Kn
    -0.07
    ��
    -0.06
    .va
    -0.06
    jay
    -0.06
    凝
    -0.06
     temas
    -0.06
    #pragma
    -0.06
    ylland
    -0.06
    oro
    -0.06
    POSITIVE LOGITS
    (length
    0.06
     QHBoxLayout
    0.06
    。また
    0.06
     modified
    0.06
    536
    0.06
     ortadan
    0.06
     علاق
    0.06
    quad
    0.06
    �
    0.06
     vyj
    0.06
    Act Density 0.002%

    No Known Activations