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

    Neuronpedia

    INDEX
    Explanations

    UI code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    然后再
    0.61
     legends
    0.58
    お待ち
    0.57
     زیادہ
    0.55
     చివరి
    0.55
    意大利
    0.54
     ఆలో
    0.54
    模式
    0.53
     slugs
    0.52
     VEGFR
    0.52
    POSITIVE LOGITS
    લ
    0.55
     Portal
    0.54
    ayant
    0.52
    AMOUNT
    0.52
     olsa
    0.52
     ある
    0.51
     labile
    0.51
    uras
    0.50
    ড়ি
    0.50
    ъл
    0.50
    Act Density 0.009%

    No Known Activations