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

    Neuronpedia

    INDEX
    Explanations

    `<!DOCTYPE html>`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الدولة
    0.45
     الشركات
    0.45
    👇
    0.45
     empresas
    0.44
     Jiangsu
    0.44
     事業
    0.44
     gospod
    0.44
     Государ
    0.44
    言語
    0.44
     宮
    0.44
    POSITIVE LOGITS
     tremendous
    0.42
     upward
    0.42
    лах
    0.41
    alem
    0.40
    endregion
    0.39
    aturen
    0.38
     symbolizes
    0.38
    rava
    0.37
     பற்றிய
    0.37
    dala
    0.37
    Act Density 0.000%

    No Known Activations