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

    Neuronpedia

    INDEX
    Explanations

    omega 3 and section 8

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ola
    -0.06
     candy
    -0.06
    (domain
    -0.06
     nested
    -0.06
    fuck
    -0.06
     страны
    -0.06
     shiny
    -0.06
     शब
    -0.06
    objet
    -0.06
     ribbon
    -0.06
    POSITIVE LOGITS
    １
    0.08
    2
    0.08
    5
    0.08
    3
    0.07
     Emails
    0.07
    ２
    0.07
    ุงเทพ
    0.07
    آخر
    0.07
    疾
    0.07
     두
    0.07
    Act Density 0.201%

    No Known Activations