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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    试点
    -0.07
     gql
    -0.07
    rather
    -0.07
    他认为
    -0.07
    当今
    -0.07
    🧿
    -0.07
    availability
    -0.07
    .hl
    -0.06
     الكريم
    -0.06
    טכנולוגיה
    -0.06
    POSITIVE LOGITS
     Paradise
    0.07
    Pose
    0.07
     buyer
    0.06
    ㈹
    0.06
    .watch
    0.06
     Head
    0.06
     twilight
    0.06
    🏿
    0.06
     ноя
    0.06
     [=[
    0.06
    Act Density 0.003%

    No Known Activations