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

    Neuronpedia

    INDEX
    Explanations

    various texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    –↵↵
    -0.31
    è¢ĭ
    -0.30
    mony
    -0.26
    æį®
    -0.26
    èħIJè´¥
    -0.26
    å°±æѤ
    -0.24
    ocale
    -0.24
    å¸IJ
    -0.24
    (Pos
    -0.24
    åºıåĪĹ
    -0.24
    POSITIVE LOGITS
     apologize
    0.28
    åŃĹåı·
    0.26
     minute
    0.26
    å½Ī
    0.25
    apur
    0.25
    ä¸įæİĴéĻ¤
    0.25
     fifth
    0.25
     DÅ©ng
    0.25
    æ»ļ
    0.25
    代谢
    0.24
    Act Density 0.004%

    No Known Activations