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

    Neuronpedia

    INDEX
    Explanations

    authors and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     सरदार
    0.65
     brochure
    0.65
    ัด
    0.61
    コク
    0.61
     brochures
    0.59
     position
    0.57
    位置
    0.56
    จำ
    0.56
    ranet
    0.56
    bookmark
    0.55
    POSITIVE LOGITS
     Josh
    1.31
     Jordan
    1.31
     Matt
    1.24
     Zack
    1.22
     Zach
    1.20
     Ryan
    1.16
    Josh
    1.16
     jordan
    1.14
     Tyler
    1.13
     Dylan
    1.12
    Act Density 0.042%

    No Known Activations