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

    Neuronpedia

    INDEX
    Explanations

    database records

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ãĤĭãĤĪãģĨãģ«
    -0.25
    arms
    -0.25
     arms
    -0.25
    便åĪ©
    -0.25
    unci
    -0.24
    ije
    -0.24
    æĸ¹ãģ¯
    -0.24
    avery
    -0.24
    ycles
    -0.24
     tight
    -0.23
    POSITIVE LOGITS
    æķĪæŀľåĽ¾
    0.26
    çĮ
    0.26
    OCK
    0.26
    è¹Ģ
    0.25
     suspense
    0.25
    (es
    0.25
    åĶ¾
    0.25
    以ä¸ĬçļĦ
    0.24
    é«ĺæ¡£
    0.24
    å·®ä¸įå¤ļ
    0.24
    Act Density 0.198%

    No Known Activations