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

    Neuronpedia

    INDEX
    Explanations

    .The

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    するのが
    0.29
     यहां
    0.26
    為什麼
    0.26
     aquí
    0.25
     aqui
    0.25
     здесь
    0.25
    タイトル
    0.25
     여기서
    0.25
    为什么
    0.24
    我们在
    0.24
    POSITIVE LOGITS
     Meanwhile
    0.38
    Meanwhile
    0.38
     According
    0.34
     meanwhile
    0.34
     Representatives
    0.34
    According
    0.32
    한편
    0.31
     Speaking
    0.30
     Currently
    0.30
    Representatives
    0.30
    Act Density 0.000%

    No Known Activations