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

    Neuronpedia

    INDEX
    Explanations

    table summaries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ണ്യ
    0.72
    imismo
    0.69
     Núñez
    0.67
    outro
    0.66
    フィル
    0.65
    сной
    0.65
     সম্পাদক
    0.65
     پیغام
    0.65
    ուր
    0.64
    rhinoceros
    0.64
    POSITIVE LOGITS
     |
    1.97
    {|
    1.61
    |
    1.55
    }|
    1.34
    |"
    1.30
    |[
    1.30
     $|
    1.25
     {|
    1.25
    |(
    1.22
    ]|
    1.19
    Act Density 0.032%

    No Known Activations