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

    Neuronpedia

    INDEX
    Explanations

    -app

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dew
    -0.07
    .getTarget
    -0.07
     doctoral
    -0.07
     ds
    -0.06
     GREEN
    -0.06
     prepar
    -0.06
     texto
    -0.06
     адрес
    -0.06
    Normalization
    -0.06
     keyboard
    -0.06
    POSITIVE LOGITS
     배우
    0.07
    ']}↵
    0.07
    _im
    0.07
    
    0.06
    Fixed
    0.06
    ...
    0.06
    Recommend
    0.06
    //
↵
↵
    0.06
     altro
    0.06
    ="">
↵
    0.06
    Act Density 0.001%

    No Known Activations