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
     مط
    -0.07
    _clip
    -0.07
     pac
    -0.07
     organize
    -0.06
    "class
    -0.06
     Nightmare
    -0.06
     (("
    -0.06
     Ug
    -0.06
    (chip
    -0.06
    /dd
    -0.06
    POSITIVE LOGITS
     Mohamed
    0.08
    getList
    0.08
     ocean
    0.07
     Wa
    0.06
    apia
    0.06
     Va
    0.06
     Bosnia
    0.06
    consin
    0.06
    eria
    0.06
     Wisconsin
    0.06
    Act Density 0.031%

    No Known Activations