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

    Neuronpedia

    INDEX
    Explanations

    D

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    çīĮ
    -0.27
    åŃ°
    -0.26
    示æĦı
    -0.25
    ipi
    -0.25
     SEND
    -0.24
    ublisher
    -0.24
    onders
    -0.24
    perimental
    -0.24
     Bundy
    -0.23
    åŃĢ
    -0.23
    POSITIVE LOGITS
    åĩ¿
    0.30
    æ¸ħæ´ģ
    0.28
    disc
    0.28
    æĸĩç§ij
    0.25
    clean
    0.25
    assin
    0.25
    jaw
    0.25
    -clean
    0.25
    ä¸įè´Ł
    0.24
    åĭĺæİ¢
    0.24
    Act Density 3.138%

    No Known Activations