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

    Neuronpedia

    INDEX
    Explanations

    sections and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ürlich
    0.30
     pengurangan
    0.29
    房子
    0.29
     തവണ
    0.29
     최대한
    0.29
     程序
    0.28
     disappro
    0.28
    每個
    0.28
    mless
    0.28
     semicircle
    0.28
    POSITIVE LOGITS
    5
    0.32
    2
    0.29
     বাণিজ্য
    0.28
    1
    0.27
    KB
    0.27
     Webinar
    0.27
    7
    0.26
    9
    0.26
    Guide
    0.26
    HR
    0.26
    Act Density 0.107%

    No Known Activations