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

    Neuronpedia

    INDEX
    Explanations

    technical modules or installations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ელ
    0.70
     unknowns
    0.68
     solid
    0.64
     unknown
    0.62
    prof
    0.62
    Counters
    0.61
    爱好
    0.61
     neg
    0.61
    inke
    0.61
    Anomaly
    0.60
    POSITIVE LOGITS
     ジャ
    0.75
    iduría
    0.73
     الرا
    0.72
    圍
    0.72
    ందించ
    0.71
     dibuj
    0.71
    JPN
    0.70
    屉
    0.69
    围
    0.68
     பயிற்
    0.68
    Act Density 0.003%

    No Known Activations