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
    desk
    -0.28
    loc
    -0.26
    æĬķåħ¥åĪ°
    -0.26
    åİĭ
    -0.26
    转
    -0.25
    éĽħ
    -0.25
     feed
    -0.24
    ยะ
    -0.24
     redirected
    -0.24
    cribe
    -0.24
    POSITIVE LOGITS
    vation
    0.27
     nd
    0.26
    éĻ£
    0.25
    VIEW
    0.25
    ARING
    0.25
    æīĪ
    0.24
    çݯå¢ĥä¸ĭ
    0.24
    ieval
    0.24
    emin
    0.23
     Colts
    0.23
    Act Density 3.413%

    No Known Activations