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

    Neuronpedia

    INDEX
    Explanations

    range

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ystone
    -0.29
    geries
    -0.28
     sag
    -0.28
    aron
    -0.28
    uden
    -0.25
    aira
    -0.25
    åIJĦ级
    -0.24
    ÑĢÑıд
    -0.24
     Expect
    -0.24
    ear
    -0.24
    POSITIVE LOGITS
     Pty
    0.27
    èĢĥçłĶ
    0.26
    OfSize
    0.25
     cess
    0.24
    æĮĩçĿĢ
    0.24
    .transition
    0.24
    Ø´Ùĩ
    0.24
    entr
    0.24
    æĮ¥æīĭ
    0.24
    OSH
    0.23
    Act Density 1.541%

    No Known Activations