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

    Neuronpedia

    INDEX
    Explanations

    9

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     NSK
    -0.28
    éģĩä¸Ĭ
    -0.26
    (END
    -0.25
    åIJ»
    -0.25
     exhibited
    -0.25
     addUser
    -0.24
     RSVP
    -0.24
    ERS
    -0.23
    çIJĨ解åĴĮ
    -0.23
    Oct
    -0.23
    POSITIVE LOGITS
    èİĵ
    0.29
    >|
    0.28
     chim
    0.27
    azor
    0.25
    altern
    0.25
    俾
    0.25
    ishing
    0.23
    '|
    0.23
    æŶä¸į
    0.23
    ãģªãĤĬ
    0.23
    Act Density 0.053%

    No Known Activations