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

    Neuronpedia

    INDEX
    Explanations

    starting with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    continued
    0.81
     продов
    0.78
    continues
    0.71
    Continued
    0.71
     Послед
    0.68
     masih
    0.68
    oL
    0.68
     нет
    0.67
    ستم
    0.66
    왔
    0.65
    POSITIVE LOGITS
     afresh
    1.33
    आती
    1.14
     anew
    1.14
     hostilities
    1.09
     experimenting
    1.04
    ຕົ
    1.00
     timer
    0.99
     planning
    0.92
     timers
    0.91
     reaping
    0.89
    Act Density 0.143%

    No Known Activations