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

    Neuronpedia

    INDEX
    Explanations

    creates a new

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     구축
    0.87
    打造
    0.86
    を展開
    0.86
     கட்டமை
    0.82
     자랑
    0.82
     sieci
    0.81
    anfaatkan
    0.80
     revitalize
    0.80
     ullam
    0.79
     viable
    0.79
    POSITIVE LOGITS
     বা
    0.83
    または
    0.67
     deciduous
    0.67
     или
    0.66
     ಅಥವಾ
    0.64
     أو
    0.63
    或
    0.63
     culprits
    0.63
     or
    0.62
    Lack
    0.62
    Act Density 0.120%

    No Known Activations