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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     откры
    -0.07
     damage
    -0.07
    ूच
    -0.06
     ROUND
    -0.06
     loi
    -0.06
    orks
    -0.06
     Burada
    -0.06
    adays
    -0.06
    883
    -0.06
    /layout
    -0.06
    POSITIVE LOGITS
    IGATION
    0.07
    луата
    0.06
    monary
    0.06
    풍
    0.06
     affirmative
    0.06
     aval
    0.06
     Patriot
    0.06
    Prior
    0.06
    rots
    0.06
    .person
    0.06
    Act Density 0.031%

    No Known Activations