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
    順
    -0.07
     Hindered
    -0.06
    -expand
    -0.06
     avan
    -0.06
     constrained
    -0.06
    Les
    -0.06
    邪
    -0.06
    Codigo
    -0.06
    인은
    -0.06
     bake
    -0.06
    POSITIVE LOGITS
     norm
    0.07
     compensated
    0.07
     protesters
    0.07
     dow
    0.07
     permanent
    0.06
     태
    0.06
     голос
    0.06
     метал
    0.06
     compliance
    0.06
    XR
    0.06
    Act Density 0.011%

    No Known Activations