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

    Neuronpedia

    INDEX
    Explanations

    Numerical measurements, groupings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Collection
    -0.07
     Les
    -0.07
     politically
    -0.06
    集中
    -0.06
    emacs
    -0.06
     Liberals
    -0.06
    thesize
    -0.06
     konusu
    -0.06
     Ders
    -0.06
    oriented
    -0.06
    POSITIVE LOGITS
    _timestamp
    0.07
    RY
    0.07
    -comments
    0.06
    _mm
    0.06
     {↵↵↵↵
    0.06
    _SPEC
    0.06
    _simps
    0.06
    ],'
    0.06
     {};
    0.06
    ])).
    0.06
    Act Density 0.018%

    No Known Activations