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

    Neuronpedia

    INDEX
    Explanations

    explanatory notes or disclaimers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     सिस्टम
    0.49
    がたくさん
    0.46
     সিস্টেম
    0.46
    NA
    0.44
    unya
    0.44
    RAW
    0.43
    انی
    0.43
     نظام
    0.43
    Have
    0.43
    IC
    0.42
    POSITIVE LOGITS
    버지
    0.55
    acij
    0.46
     consumed
    0.45
    ῎
    0.45
    seits
    0.45
    धरी
    0.43
     ObjData
    0.43
     grooming
    0.43
     тру
    0.43
    doğan
    0.42
    Act Density 0.001%

    No Known Activations