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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    monkey
    -0.07
    _text
    -0.06
    (drop
    -0.06
     predecess
    -0.06
    ies
    -0.06
    (dat
    -0.06
    e
    -0.06
     Attorney
    -0.06
     حک
    -0.06
     Ken
    -0.06
    POSITIVE LOGITS
     služ
    0.06
     infuri
    0.06
    -react
    0.06
     мех
    0.06
    ,module
    0.06
    =create
    0.06
    Navigation
    0.06
    .splice
    0.06
     sights
    0.06
     Shelby
    0.06
    Act Density 0.039%

    No Known Activations