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

    Neuronpedia

    INDEX
    Explanations

    postcode

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    יי
    0.56
    max
    0.55
    print
    0.54
    pay
    0.53
    port
    0.52
    ub
    0.51
    Start
    0.50
    set
    0.50
    con
    0.50
    pt
    0.50
    POSITIVE LOGITS
     ሁኔታ
    0.58
     rời
    0.57
     Фурга
    0.57
    ဆံ
    0.56
    ጋገብ
    0.55
    czeń
    0.55
     appreciates
    0.53
    的机会
    0.52
     belladone
    0.52
     отмечает
    0.52
    Act Density 0.008%

    No Known Activations