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

    Neuronpedia

    INDEX
    Explanations

    lock

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vidět
    -0.07
     李
    -0.07
     taxation
    -0.07
     Coast
    -0.07
    -la
    -0.07
     measurements
    -0.06
     liền
    -0.06
     střed
    -0.06
    руп
    -0.06
    ../
    -0.06
    POSITIVE LOGITS
     Pars
    0.06
    ={{
    0.06
    영어
    0.06
     Toolkit
    0.06
     Innovative
    0.06
     الشي
    0.05
    outine
    0.05
    (reason
    0.05
     tweaks
    0.05
    。↵↵
    0.05
    Act Density 0.006%

    No Known Activations