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

    Neuronpedia

    INDEX
    Explanations

    low effort, low time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    های
    0.42
    pecific
    0.40
    orthogonal
    0.39
    ની
    0.39
     અન્ય
    0.39
    onium
    0.38
    變成
    0.38
    getDefault
    0.38
    هاي
    0.37
    อยู่ใน
    0.37
    POSITIVE LOGITS
     സമയം
    0.46
     deeds
    0.43
     рішення
    0.40
     遅く
    0.40
     storie
    0.38
     Ames
    0.38
     документы
    0.38
     repost
    0.38
     решение
    0.37
     forbearance
    0.37
    Act Density 0.120%

    No Known Activations