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

    Neuronpedia

    INDEX
    Explanations

    say code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     geographic
    -0.07
     Bought
    -0.07
     intens
    -0.07
    co
    -0.07
    .');↵
    -0.07
     weaknesses
    -0.06
    Summary
    -0.06
    ead
    -0.06
    customer
    -0.06
     psych
    -0.06
    POSITIVE LOGITS
     somew
    0.06
    GEST
    0.06
    르게
    0.06
    aría
    0.06
     InputStreamReader
    0.06
    ılıyor
    0.06
    WithDuration
    0.06
    Выб
    0.06
    =-=-=-=-
    0.06
     Excellent
    0.06
    Act Density 0.002%

    No Known Activations