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

    Neuronpedia

    INDEX
    Explanations

    Polenta recipes method: 2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     attempts
    -0.08
     Le
    -0.08
     Optimize
    -0.08
    elua
    -0.08
     confidentiality
    -0.07
     explosion
    -0.07
    dry
    -0.07
     Attempt
    -0.07
    angel
    -0.07
    Attempt
    -0.07
    POSITIVE LOGITS
     flowed
    0.10
     pagar
    0.09
     flowing
    0.09
    -paying
    0.08
     steamed
    0.08
     monoc
    0.08
    -flow
    0.08
     magna
    0.07
     нех
    0.07
     ночью
    0.07
    Act Density 0.001%

    No Known Activations