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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     legalization
    -0.07
     demonstrated
    -0.07
     eliminate
    -0.07
     DEM
    -0.07
    Э
    -0.07
     Coverage
    -0.07
    _nom
    -0.07
     Rud
    -0.06
     Bott
    -0.06
     Geh
    -0.06
    POSITIVE LOGITS
    ileceği
    0.07
    /swagger
    0.06
     overturn
    0.06
     menší
    0.06
     spender
    0.06
    .userInfo
    0.06
    �
    0.06
     Raphael
    0.05
     Tropical
    0.05
     quyết
    0.05
    Act Density 0.009%

    No Known Activations