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

    Neuronpedia

    INDEX
    Explanations

    surgery

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    omat
    -0.33
    åĨ¬
    -0.30
    hound
    -0.29
    rouw
    -0.26
    ä¸įæĸŃæī©å¤§
    -0.26
    ÑĢÑıд
    -0.24
    æī©å¤§
    -0.24
    åľ¨éĩĮéĿ¢
    -0.24
    ×ķתר
    -0.24
     summers
    -0.23
    POSITIVE LOGITS
    IPP
    0.27
    mod
    0.25
     trÃŃ
    0.25
     nab
    0.25
    æī¶
    0.25
    峡
    0.25
    aland
    0.25
     mod
    0.25
    åħ¸åŀĭçļĦ
    0.25
     Wilmington
    0.25
    Act Density 0.001%

    No Known Activations