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

    Neuronpedia

    INDEX
    Explanations

    Numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    艾
    -0.07
    다는
    -0.07
     institutional
    -0.06
    European
    -0.06
     sf
    -0.06
     Hose
    -0.06
    Fly
    -0.06
     funnel
    -0.06
     Asian
    -0.06
    чих
    -0.06
    POSITIVE LOGITS
     ->
    0.07
    .stage
    0.06
                
    0.06
    δρα
    0.06
     script
    0.06
     Dinner
    0.06
    ");
    0.06
     aku
    0.06
     कब
    0.06
     oath
    0.06
    Act Density 0.012%

    No Known Activations