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

    Neuronpedia

    INDEX
    Explanations

    mechanical systems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uentes
    -0.07
     mile
    -0.07
    urt
    -0.06
    enie
    -0.06
     interpretation
    -0.06
    .%
    -0.06
    ylinder
    -0.06
     thief
    -0.06
    -mile
    -0.06
    \Array
    -0.06
    POSITIVE LOGITS
    持续
    0.07
     chứa
    0.07
    Autoresizing
    0.07
    错
    0.06
     تس
    0.06
    	Input
    0.06
     Лу
    0.06
     puan
    0.06
    气
    0.06
     новых
    0.06
    Act Density 0.043%

    No Known Activations