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

    Neuronpedia

    INDEX
    Explanations

    what do you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     perennial
    0.90
    )
    0.88
    пример
    0.87
     dieser
    0.87
     delirium
    0.84
    त्त
    0.83
    я
    0.81
     memorandum
    0.81
     memoranda
    0.81
     следует
    0.80
    POSITIVE LOGITS
    ০০
    0.78
     زینت
    0.77
    chas
    0.75
    śnie
    0.74
    iya
    0.73
    lös
    0.72
    ほど
    0.70
    毕竟
    0.70
    就好
    0.70
    avila
    0.70
    Act Density 0.000%

    No Known Activations