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

    Neuronpedia

    INDEX
    Explanations

    after relief or EOS

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    透露
    0.43
    𒉺
    0.41
     δὲ
    0.39
     действи
    0.39
    ధిక
    0.38
     genoeg
    0.38
     DEALINGS
    0.38
    אות
    0.38
    ާތ
    0.38
    𝒇
    0.37
    POSITIVE LOGITS
    master
    0.39
    "><!--
    0.39
    lazy
    0.38
    iv
    0.38
    eria
    0.37
    icone
    0.37
     বন্ধুরা
    0.37
     Ophthalmology
    0.37
    failure
    0.36
     পণ্ডিত
    0.36
    Act Density 0.000%

    No Known Activations