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

    Neuronpedia

    INDEX
    Explanations

    local conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ាញ
    0.51
     जाना
    0.50
     posthum
    0.47
    ូង
    0.47
    culis
    0.47
     undes
    0.47
    aciju
    0.46
    EDES
    0.46
    eded
    0.46
     এডিনবার্গ
    0.46
    POSITIVE LOGITS
    ปี
    0.43
    )).
    0.41
    0.40
    .
    0.39
     inspiring
    0.39
     آئینے
    0.39
    Nature
    0.39
     Over
    0.38
     Inspire
    0.38
     orchestral
    0.38
    Act Density 0.002%

    No Known Activations