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

    Neuronpedia

    INDEX
    Explanations

    academic fields and sciences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    中國
    0.61
     China
    0.57
    จีน
    0.55
     الصين
    0.55
    China
    0.55
    चीन
    0.54
    中国
    0.52
    china
    0.51
     أبو
    0.51
     চীন
    0.50
    POSITIVE LOGITS
     beat
    0.45
     snippet
    0.45
     ac
    0.41
     status
    0.41
     page
    0.40
     repeat
    0.40
     hall
    0.40
     snow
    0.39
     hello
    0.39
     panel
    0.39
    Act Density 0.002%

    No Known Activations