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

    Neuronpedia

    INDEX
    Explanations

    code, programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     highlighting
    -0.08
    ۵۰
    -0.07
     دین
    -0.07
    ्ध
    -0.06
    ضوع
    -0.06
    جيل
    -0.06
    \Mail
    -0.06
     UT
    -0.06
     увагу
    -0.06
     наруш
    -0.06
    POSITIVE LOGITS
     Prototype
    0.06
     confession
    0.06
    �
    0.06
    _IMG
    0.06
    •
    0.06
     Eigen
    0.06
    ahan
    0.06
     Lamar
    0.06
    Proceed
    0.06
    络
    0.06
    Act Density 0.245%

    No Known Activations