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
    ance
    -0.28
     sqr
    -0.26
    ANCE
    -0.26
     DER
    -0.25
    omial
    -0.25
    /octet
    -0.25
    Launcher
    -0.25
    deer
    -0.24
    IZER
    -0.24
    èģª
    -0.24
    POSITIVE LOGITS
     nip
    0.28
     doPost
    0.28
     select
    0.27
    åĮı
    0.26
    ä¸į说
    0.26
     nowhere
    0.26
    ä¸įåĬ¨
    0.25
    æīĵå¾Ĺ
    0.25
     medic
    0.24
     Hast
    0.24
    Act Density 0.022%

    No Known Activations