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

    Neuronpedia

    INDEX
    Explanations

    he or she speaks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    plements
    0.57
    ↵↵↵
    0.55
    ↵↵
    0.55
    </div>
    0.52
     youll
    0.50
    😙
    0.49
    ↵↵↵↵
    0.48
     optionally
    0.48
     antider
    0.48
     вас
    0.48
    POSITIVE LOGITS
     เขา
    0.73
    他說
    0.73
    他说
    0.73
     “[
    0.70
     "[
    0.69
    彼は
    0.69
    他在
    0.68
    "[
    0.65
     그는
    0.64
    “[
    0.62
    Act Density 0.000%

    No Known Activations