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

    Neuronpedia

    INDEX
    Explanations

    court cases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ý
    -0.07
    楞
    -0.07
    狷
    -0.07
     mł
    -0.07
    لوح
    -0.07
     JS
    -0.07
    .IsSuccess
    -0.07
    �
    -0.06
    Dynamic
    -0.06
     foc
    -0.06
    POSITIVE LOGITS
     gamer
    0.07
     calories
    0.07
    ’hui
    0.06
     dick
    0.06
     order
    0.06
    颁发
    0.06
     Reeves
    0.06
    şi
    0.06
    vais
    0.06
     Klein
    0.06
    Act Density 0.003%

    No Known Activations