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

    Neuronpedia

    INDEX
    Explanations

    New York Times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    நிலையில்
    0.57
     तिमाही
    0.56
    த்துவம்
    0.56
    မြင်
    0.55
     ಯಾವ
    0.52
    ťou
    0.52
    랗
    0.52
    បី
    0.51
     ಕ್ಷ
    0.51
    LLCATS
    0.51
    POSITIVE LOGITS
     i
    0.63
    AG
    0.62
     {
    0.59
    0.55
    ิ
    0.52
     perbedaan
    0.50
    t
    0.50
     AG
    0.49
    AH
    0.48
     åp
    0.48
    Act Density 0.001%

    No Known Activations