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

    Neuronpedia

    INDEX
    Explanations

    ` and `>>`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    жной
    0.92
     полностью
    0.89
    ยนต์
    0.89
    0.84
     насколько
    0.83
    мой
    0.82
    воды
    0.82
    ной
    0.79
    рыв
    0.79
    чных
    0.79
    POSITIVE LOGITS
    ilo
    0.75
    ailles
    0.73
    iaire
    0.71
    aa
    0.71
     côté
    0.71
     que
    0.70
    ao
    0.70
    aaa
    0.69
     Failed
    0.69
    ping
    0.68
    Act Density 0.001%

    No Known Activations