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

    Neuronpedia

    INDEX
    Explanations

    verb or unified

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     binatang
    0.50
     CPA
    0.48
    sembled
    0.46
     महाप
    0.46
     CGC
    0.45
     EMEA
    0.44
     produk
    0.44
     KPMG
    0.44
     akik
    0.43
     फोर
    0.43
    POSITIVE LOGITS
     communicate
    0.43
    ن
    0.43
    ע
    0.41
    用
    0.40
    น
    0.40
    命令
    0.40
    使用
    0.39
    He
    0.38
    ού
    0.38
    Scr
    0.38
    Act Density 0.003%

    No Known Activations