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

    Neuronpedia

    INDEX
    Explanations

    data definitions and assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    䐝
    0.41
     Hone
    0.40
     siglas
    0.39
     Tram
    0.39
     dined
    0.39
     {,
    0.38
    FANG
    0.38
     Reagan
    0.38
     Goff
    0.38
     Prodig
    0.38
    POSITIVE LOGITS
    کھ
    0.48
    一
    0.48
    gets
    0.44
    给自己
    0.43
    Additional
    0.42
    Gets
    0.42
     दिया
    0.41
    0.41
    ें
    0.41
    ไหล
    0.41
    Act Density 0.012%

    No Known Activations