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

    Neuronpedia

    INDEX
    Explanations

    published by or in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     isIn
    1.56
     poved
    1.45
     sortes
    1.41
    %%%%%%%%%%%%
    1.33
    addLine
    1.33
     ![](
    1.32
     alkene
    1.32
    将
    1.32
     случа
    1.31
    涤
    1.30
    POSITIVE LOGITS
    р
    1.61
    𝘣
    1.53
    𝘺
    1.47
    𝘬
    1.40
    𝘰
    1.38
    𝘴
    1.33
    𝘵
    1.28
    𝘢
    1.27
    ना
    1.24
    𝘷
    1.22
    Act Density 0.004%

    No Known Activations