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

    Neuronpedia

    INDEX
    Explanations

    you believe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ющей
    0.71
    ەل
    0.68
    สิ่ง
    0.65
    $/.
    0.64
    払い
    0.64
    తల
    0.62
    іга
    0.62
     Piv
    0.61
    bans
    0.60
    спе
    0.60
    POSITIVE LOGITS
     பெரி
    0.68
     extensions
    0.67
     extension
    0.66
     Lampung
    0.64
     dap
    0.64
     سماعت
    0.63
     Extensions
    0.62
     vergleich
    0.62
     डेंटल
    0.62
    extension
    0.62
    Act Density 0.000%

    No Known Activations