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
     trace
    -0.07
     Trace
    -0.06
    権
    -0.06
     faith
    -0.06
     лег
    -0.06
     villain
    -0.06
     ch
    -0.06
    	il
    -0.06
    question
    -0.06
    เล
    -0.06
    POSITIVE LOGITS
    _SEGMENT
    0.07
    elocity
    0.07
    ocal
    0.07
    (Dense
    0.07
    acet
    0.06
     neon
    0.06
    ká
    0.06
     조회
    0.06
     Gle
    0.06
    autoload
    0.06
    Act Density 0.016%

    No Known Activations