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

    Neuronpedia

    INDEX
    Explanations

    third, fourth, fifth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uta
    0.41
    ေါ
    0.40
    paused
    0.38
     stesse
    0.37
     gleichen
    0.37
     paused
    0.36
    SOs
    0.36
     simili
    0.36
    uosa
    0.36
    đa
    0.35
    POSITIVE LOGITS
     Third
    0.98
     third
    0.98
    Third
    0.97
    第三
    0.81
     THIRD
    0.81
     graders
    0.79
     তৃতীয়
    0.79
     الثالث
    0.79
     треть
    0.77
    third
    0.77
    Act Density 0.023%

    No Known Activations