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

    Neuronpedia

    INDEX
    Explanations

    explaining why facts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    تمام
    0.52
     jullie
    0.50
     volledig
    0.46
     einzige
    0.45
     gesam
    0.44
    óc
    0.43
    ادت
    0.43
    эле
    0.43
     {*}
    0.42
     noche
    0.41
    POSITIVE LOGITS
    mation
    0.45
     zoos
    0.44
    million
    0.43
    RESSION
    0.43
    cı
    0.42
    ការពារ
    0.42
    tection
    0.42
     desorption
    0.41
    翩
    0.41
     साथी
    0.41
    Act Density 0.001%

    No Known Activations