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

    Neuronpedia

    INDEX
    Explanations

    durations or quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ४
    0.68
     ਅਤੇ
    0.61
     B
    0.60
    人和
    0.60
     ஆனால்
    0.59
    人と
    0.58
    abhave
    0.57
     Meeting
    0.57
     Realm
    0.57
     abhiv
    0.57
    POSITIVE LOGITS
    ق
    0.96
    ك
    0.87
    q
    0.83
    Q
    0.75
    ا
    0.74
    years
    0.73
    你
    0.73
    M
    0.71
    is
    0.70
    X
    0.69
    Act Density 0.300%

    No Known Activations