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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _timeout
    -0.07
    (bytes
    -0.06
    lates
    -0.06
    PasswordEncoder
    -0.06
    кас
    -0.06
    -delete
    -0.06
     datasource
    -0.06
     вибор
    -0.06
    ต
    -0.06
    	↵	↵	↵	↵
    -0.06
    POSITIVE LOGITS
    /Math
    0.08
     Beta
    0.08
     Slut
    0.07
     destinationViewController
    0.07
    .setParameter
    0.07
     ‏
    0.07
     감
    0.06
     eff
    0.06
    ichern
    0.06
    幸福
    0.06
    Act Density 0.024%

    No Known Activations