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

    Neuronpedia

    INDEX
    Explanations

    table

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    98
    -0.07
    emia
    -0.07
    lecture
    -0.07
    lp
    -0.06
     Layout
    -0.06
     Watching
    -0.06
    memory
    -0.06
    _ls
    -0.06
    bolt
    -0.06
    _REGION
    -0.06
    POSITIVE LOGITS
     avoid
    0.07
     日本
    0.07
     unconventional
    0.06
    .SOCK
    0.06
     дра
    0.06
    (statearr
    0.06
    .lastIndexOf
    0.06
     dracon
    0.06
    .amazon
    0.06
     actionTypes
    0.06
    Act Density 0.057%

    No Known Activations