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

    Neuronpedia

    INDEX
    Explanations

    background-

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Украина
    0.92
    FindingsRequest
    0.90
    ாந்து
    0.88
    させ
    0.84
     смерть
    0.84
    一定的
    0.84
     Украи
    0.83
    ваете
    0.82
    练习
    0.81
    瓔
    0.81
    POSITIVE LOGITS
    ira
    0.77
    adir
    0.77
    l
    0.76
     ist
    0.75
    ki
    0.72
    igh
    0.71
     h
    0.70
     find
    0.70
    ka
    0.70
     ol
    0.69
    Act Density 0.002%

    No Known Activations