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

    Neuronpedia

    INDEX
    Explanations

    circulating

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    èĨº
    -0.29
     terminal
    -0.28
    ä¸Ģè§Ī
    -0.26
     skl
    -0.25
    ä¸įæŃ¢
    -0.25
    /Sub
    -0.25
     convert
    -0.25
    lse
    -0.25
     ë¨
    -0.24
    ä¸į平衡
    -0.24
    POSITIVE LOGITS
    åĪĨå±Ģ
    0.28
     Song
    0.27
     Tango
    0.26
    æĻ°
    0.26
    _ev
    0.25
    梧
    0.25
     öz
    0.25
    Song
    0.24
    otify
    0.24
     ev
    0.24
    Act Density 0.009%

    No Known Activations