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

    Neuronpedia

    INDEX
    Explanations

    lists, options, comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     trance
    -0.07
     tents
    -0.07
     mothers
    -0.06
     배
    -0.06
     Get
    -0.06
     Honey
    -0.06
     Tong
    -0.06
     але
    -0.06
     DB
    -0.06
     lược
    -0.06
    POSITIVE LOGITS
    „ط
    0.07
    clarsimp
    0.07
    σε
    0.07
     Inline
    0.07
    Squared
    0.07
     collects
    0.06
    gps
    0.06
     Planner
    0.06
    lian
    0.06
    Bounding
    0.06
    Act Density 0.066%

    No Known Activations