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

    Neuronpedia

    INDEX
    Explanations

    64 or 32

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     RV
    -0.07
    ी-
    -0.06
    /articles
    -0.06
    ために
    -0.06
     некоторые
    -0.06
     správ
    -0.06
    	ref
    -0.06
    .SO
    -0.06
    .restaurant
    -0.06
    HomeAs
    -0.06
    POSITIVE LOGITS
    aired
    0.07
     trenches
    0.06
    Aggregate
    0.06
    apsed
    0.06
    -flex
    0.06
     Dominion
    0.06
    ocab
    0.06
     fantasy
    0.06
    �프
    0.06
     Crowley
    0.06
    Act Density 0.001%

    No Known Activations