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

    Neuronpedia

    INDEX
    Explanations

    beer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    national
    -0.07
     Bölgesi
    -0.07
     Heights
    -0.07
    昭
    -0.07
     privileges
    -0.07
     TypeError
    -0.07
    atology
    -0.06
    迎
    -0.06
    cea
    -0.06
    τικά
    -0.06
    POSITIVE LOGITS
     Sa
    0.07
    state
    0.06
    -bo
    0.06
     banana
    0.06
     resent
    0.06
    Automation
    0.05
     used
    0.05
     Mobile
    0.05
     cube
    0.05
    χές
    0.05
    Act Density 0.002%

    No Known Activations