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

    Neuronpedia

    INDEX
    Explanations

    diverse language nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     oval
    0.46
     mrt
    0.45
     harek
    0.43
     menghad
    0.42
     mekanisme
    0.40
     dren
    0.40
     Grub
    0.39
     خدم
    0.39
     drains
    0.39
     timp
    0.39
    POSITIVE LOGITS
    édération
    0.38
     incroyable
    0.38
    सदी
    0.38
     අධ
    0.37
    Universidad
    0.37
    ConformanceMode
    0.36
    διά
    0.36
    ᒫ
    0.36
    分析
    0.36
    共通
    0.34
    Act Density 0.000%

    No Known Activations