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

    Neuronpedia

    INDEX
    Explanations

    years and significant events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    יש
    0.98
    ními
    0.95
     disponível
    0.94
     якая
    0.93
    ända
    0.91
     Física
    0.91
    𝑜
    0.91
     احنا
    0.91
    ណ្ឌ
    0.90
     تواند
    0.89
    POSITIVE LOGITS
    st
    1.35
     exemplar
    0.94
    he
    0.93
    stance
    0.86
    0.85
    stars
    0.84
     CORS
    0.82
    stal
    0.81
    com
    0.78
    dirty
    0.77
    Act Density 0.021%

    No Known Activations