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

    Neuronpedia

    INDEX
    Explanations

    medical abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     attacks
    -0.07
     errs
    -0.07
     Colleg
    -0.07
    LEVEL
    -0.07
     groin
    -0.06
    _vertex
    -0.06
    ид
    -0.06
    IZER
    -0.06
    yní
    -0.06
    废
    -0.06
    POSITIVE LOGITS
    .getInputStream
    0.06
     amph
    0.06
    Instance
    0.06
    xCD
    0.06
    .Math
    0.06
    .AddParameter
    0.06
    _friend
    0.06
     мов
    0.06
    Spi
    0.06
    							
↵
    0.06
    Act Density 0.022%

    No Known Activations