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

    Neuronpedia

    INDEX
    Explanations

    only

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ippet
    -0.07
    _MO
    -0.07
    保洁
    -0.07
     aficion
    -0.06
     caregiver
    -0.06
     Wishlist
    -0.06
     CET
    -0.06
    .Ship
    -0.06
     ==>
    -0.06
    。↵
    -0.06
    POSITIVE LOGITS
    لازم
    0.08
    复习
    0.08
    岛屿
    0.07
     Gradient
    0.07
    aterial
    0.07
    ག
    0.07
     תנאי
    0.07
     früh
    0.06
    .numberOfLines
    0.06
    UNDLE
    0.06
    Act Density 0.132%

    No Known Activations