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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     기술
    -0.07
     COPY
    -0.07
     программ
    -0.07
    Observer
    -0.06
     разви
    -0.06
     ما
    -0.06
     어려
    -0.06
     боку
    -0.06
    补
    -0.06
    Youtube
    -0.06
    POSITIVE LOGITS
    marginLeft
    0.07
     Rental
    0.06
     Costs
    0.06
    }});↵
    0.06
     Alta
    0.06
                                                    ↵
    0.06
     Apostle
    0.06
    andaş
    0.06
    eventType
    0.06
    rost
    0.06
    Act Density 0.049%

    No Known Activations