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

    Neuronpedia

    INDEX
    Explanations

    metric, linux, Loan, en

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    `:
    0.39
    ():
    0.39
     mediante
    0.38
     przez
    0.38
     dvara
    0.37
    '):
    0.37
     فاذا
    0.37
     sulle
    0.36
     complej
    0.36
     ผ่าน
    0.35
    POSITIVE LOGITS
    ۷
    0.42
    ७
    0.42
    -_
    0.40
    ج
    0.40
    Ві
    0.39
    ಅ
    0.38
    istasis
    0.37
    ۹
    0.37
     honour
    0.37
    婿
    0.36
    Act Density 0.001%

    No Known Activations