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

    Neuronpedia

    INDEX
    Explanations

    Rec-prefixed words and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    溶解
    0.70
     ensures
    0.69
     lashes
    0.69
     ensure
    0.68
    确保
    0.67
     வெள்ளி
    0.64
    ...?
    0.64
    あれば
    0.64
    带领
    0.63
     ensuring
    0.63
    POSITIVE LOGITS
    شاء
    0.71
    itives
    0.68
    ulatory
    0.65
     pieno
    0.64
    이너
    0.61
    artificial
    0.61
    ீன்
    0.60
     unreal
    0.60
     तुरु
    0.59
    鬨
    0.58
    Act Density 0.132%

    No Known Activations