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

    Neuronpedia

    INDEX
    Explanations

    search queries and results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    来说
    0.46
    䀨
    0.41
     {}>,
    0.41
    来源
    0.40
    元件
    0.40
    伱
    0.40
     Bakers
    0.40
    exch
    0.40
    js
    0.40
     действие
    0.40
    POSITIVE LOGITS
     pretože
    0.45
     kerana
    0.45
     fordi
    0.45
     pursuant
    0.43
     gambling
    0.43
     زیرا
    0.43
    ).”
    0.42
     because
    0.41
     powertrain
    0.41
    MEs
    0.40
    Act Density 0.000%

    No Known Activations