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

    Neuronpedia

    INDEX
    Explanations

    intelligent origin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    اعری
    0.45
     век
    0.44
     лишь
    0.43
    จึง
    0.39
    赚钱
    0.39
     lakini
    0.39
    лер
    0.39
     tetapi
    0.39
    ริ่ม
    0.39
    ursed
    0.39
    POSITIVE LOGITS
     diluted
    0.45
     waarde
    0.43
     specimens
    0.42
     Value
    0.40
     расстоянии
    0.39
    Укупно
    0.38
     inlay
    0.38
    ضاف
    0.38
     scavenger
    0.38
     graphite
    0.37
    Act Density 0.001%

    No Known Activations