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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ensen
    -0.27
    _Struct
    -0.25
    èĻŀ
    -0.24
    æ·±åĬłå·¥
    -0.24
    æ·±å¤Ħ
    -0.24
     ske
    -0.24
     effected
    -0.24
    çĶµåŃIJ产åĵģ
    -0.24
    çķĻå®Ī
    -0.24
    Concern
    -0.24
    POSITIVE LOGITS
     disconnect
    0.27
    æĶ¿
    0.26
    é¢ijé¢ij
    0.24
     ren
    0.24
    reed
    0.24
    æīĭå¥Ĺ
    0.24
    ä¹Łæľī
    0.24
    漫
    0.23
    era
    0.23
     preg
    0.23
    Act Density 0.004%

    No Known Activations