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
    utive
    -0.29
     slee
    -0.28
    éĥ¨
    -0.26
    åħ¹
    -0.25
     bulk
    -0.25
    æĹħ游å±Ģ
    -0.25
    bulk
    -0.24
    å·¥ç¨ĭæĬĢæľ¯
    -0.24
    屦
    -0.23
     typename
    -0.23
    POSITIVE LOGITS
    rise
    0.27
    éĺħåİĨ
    0.26
    declar
    0.26
    alars
    0.25
    岸边
    0.25
    ä¸Ģ头
    0.25
     ris
    0.24
    .CREATED
    0.24
    ashing
    0.24
     ascend
    0.24
    Act Density 0.092%

    No Known Activations