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

    Neuronpedia

    INDEX
    Explanations

    hedges and pruning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ные
    0.72
    다
    0.66
    نات
    0.61
    nements
    0.61
     sassy
    0.59
    ных
    0.58
    ný
    0.58
    nější
    0.58
    ონი
    0.58
    nymi
    0.57
    POSITIVE LOGITS
    ли
    0.79
    LE
    0.68
     âgé
    0.66
     ജോലി
    0.64
     hedge
    0.64
     hedges
    0.64
    BAR
    0.61
    ﺮ
    0.61
    are
    0.61
     নির্মাতা
    0.59
    Act Density 0.001%

    No Known Activations