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

    Neuronpedia

    INDEX
    Explanations

    Numbers or code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Apply
    -0.07
     下
    -0.07
     ').
    -0.07
    _trans
    -0.07
    emsp
    -0.06
    下的
    -0.06
    观
    -0.06
     {!!
    -0.06
    .dictionary
    -0.06
    -plugins
    -0.06
    POSITIVE LOGITS
     Blend
    0.07
     sage
    0.06
     Cycl
    0.06
     Trek
    0.06
     Composer
    0.06
     fabricated
    0.06
    ...");
↵
    0.06
     RESULTS
    0.06
     нового
    0.06
    〜
    0.06
    Act Density 0.051%

    No Known Activations