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

    Neuronpedia

    INDEX
    Explanations

    Todd

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    è§Ĥ
    -0.27
    licensed
    -0.26
     Claims
    -0.26
    /demo
    -0.26
    åĭī
    -0.25
    ä¿ĥ
    -0.25
    rou
    -0.24
    ä¸ļä½Ļ
    -0.24
     nail
    -0.24
     vig
    -0.24
    POSITIVE LOGITS
    ä¼Ĭæĭī
    0.26
    yt
    0.26
    (pt
    0.25
    踵
    0.25
    ::~
    0.25
    士
    0.24
    actus
    0.24
    .isArray
    0.24
    ÑĢак
    0.23
    PUR
    0.23
    Act Density 0.347%

    No Known Activations