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

    Neuronpedia

    INDEX
    Explanations

    names with suffixes

    np_acts-logits-general · gemini-2.5-flash-lite

    names of people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ي
    0.88
    as
    0.73
    و
    0.71
    o
    0.67
    an
    0.65
    us
    0.65
    i
    0.64
    ח
    0.63
    ни
    0.63
    ح
    0.63
    POSITIVE LOGITS
     ı
    0.51
     ഇത്
    0.49
     लाइक
    0.49
    🛰
    0.48
    保湿
    0.47
    哽
    0.47
    🈺
    0.47
     wirelessly
    0.46
     decentral
    0.46
     മാത്രമേ
    0.46
    Act Density 0.059%

    No Known Activations