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

    Neuronpedia

    INDEX
    Explanations

    likewise similarly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BITMAP
    0.77
     biota
    0.76
    бно
    0.75
    <0xE2>
    0.74
    ſs
    0.73
    贻
    0.73
     env
    0.72
    ياة
    0.72
    wiad
    0.72
    _{*}(
    0.71
    POSITIVE LOGITS
    こちらも
    2.28
    これも
    2.08
    こちらは
    1.95
     역시
    1.88
     ebenfalls
    1.79
     얘는
    1.65
     yine
    1.62
    同样
    1.61
    Another
    1.58
    another
    1.58
    Act Density 0.591%

    No Known Activations