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

    Neuronpedia

    INDEX
    Explanations

    using various languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    או
    0.47
    ก
    0.47
    8
    0.47
    3
    0.46
    но
    0.45
     mortgage
    0.44
    9
    0.44
    י
    0.42
    会
    0.41
    Mkv
    0.40
    POSITIVE LOGITS
    えない
    0.46
     grâce
    0.41
     pomocí
    0.41
     davvero
    0.41
     informática
    0.40
     utilizando
    0.38
     پن
    0.38
     باستخدام
    0.38
     abbastanza
    0.38
     lavoratori
    0.38
    Act Density 0.024%

    No Known Activations