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

    Neuronpedia

    INDEX
    Explanations

    O(n log n)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    類的
    0.43
    yles
    0.39
     <>
    0.39
    !=
    0.37
    以上的
    0.37
     सजा
    0.36
    <>
    0.36
    ather
    0.35
    ollary
    0.35
    öö
    0.35
    POSITIVE LOGITS
     potenciales
    0.40
     tric
    0.40
    tric
    0.39
    驩
    0.39
     Gottlieb
    0.39
     delving
    0.39
     Coordinate
    0.38
     cannab
    0.38
     Cann
    0.37
     황
    0.37
    Act Density 0.000%

    No Known Activations