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

    Neuronpedia

    INDEX
    Explanations

    function descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    не
    1.02
    ни
    0.75
    ون
    0.73
    ites
    0.72
    ل
    0.72
    ul
    0.70
    де
    0.70
    as
    0.67
     Но
    0.67
     Тихо
    0.67
    POSITIVE LOGITS
    യിൽ
    0.83
     mampu
    0.77
     trover
    0.77
     therein
    0.76
    车载
    0.74
     pueda
    0.72
     lashed
    0.71
    യില്‍
    0.71
    0.70
     pecul
    0.70
    Act Density 0.002%

    No Known Activations