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

    Neuronpedia

    INDEX
    Explanations

    open plan

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    v
    0.62
    ри
    0.57
     fırs
    0.54
    伤害
    0.53
    چنین
    0.53
     erode
    0.52
    깎
    0.50
     سرکاری
    0.50
     фотоап
    0.50
     inorganic
    0.49
    POSITIVE LOGITS
     remon
    0.53
     الماضي
    0.51
    esterday
    0.50
     jubil
    0.50
     feeling
    0.49
     frankly
    0.49
    ফাই
    0.49
     figlio
    0.49
    isme
    0.48
     Schmitz
    0.48
    Act Density 0.002%

    No Known Activations