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

    Neuronpedia

    INDEX
    Explanations

    recognition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hull
    -0.07
    enefit
    -0.07
     Tricks
    -0.07
     Stones
    -0.06
     spare
    -0.06
    paginate
    -0.06
    _parsed
    -0.06
     Squad
    -0.06
     Spare
    -0.06
     정말
    -0.06
    POSITIVE LOGITS
     recognized
    0.09
     recognised
    0.08
     recognize
    0.08
     recognizes
    0.08
     －
    0.07
     system
    0.06
     tracer
    0.06
     generally
    0.06
    认识
    0.06
    (so
    0.06
    Act Density 0.015%

    No Known Activations