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

    Neuronpedia

    INDEX
    Explanations

    ­

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fine
    -0.07
    ัด
    -0.06
     Men
    -0.06
     CAD
    -0.06
    Demo
    -0.06
     임
    -0.06
    lder
    -0.06
    emean
    -0.06
    Strength
    -0.06
     customary
    -0.06
    POSITIVE LOGITS
     conceived
    0.07
    ۲۱
    0.07
    icient
    0.07
    ITHUB
    0.07
    ١
    0.07
    (auth
    0.06
    (chart
    0.06
    [];
↵
    0.06
    _ty
    0.06
    .To
    0.06
    Act Density 0.005%

    No Known Activations