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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Exped
    -0.27
    gradable
    -0.26
     qued
    -0.26
    æģ¶åĬ£
    -0.26
    èĢ³è¾¹
    -0.25
    éĻ©
    -0.24
    beck
    -0.24
     FormData
    -0.24
    lood
    -0.24
    亲å¯Ĩ
    -0.24
    POSITIVE LOGITS
    æī«ä¸Ģ
    0.31
    orgeous
    0.28
    çĶ·åŃIJ
    0.27
    å±ŀäºİ
    0.27
    æĹ¢æĺ¯
    0.27
    ":"/
    0.25
     Passage
    0.25
    tons
    0.24
     balance
    0.24
    æłĩçļĦ
    0.24
    Act Density 0.822%

    No Known Activations