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

    Neuronpedia

    INDEX
    Explanations

    information processing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ioc
    0.44
     ভ্রমণ
    0.43
    തിനാ
    0.40
    iosa
    0.38
     வெளி
    0.38
     चाहती
    0.38
    ರಿಸಿ
    0.37
     FED
    0.37
     веб
    0.37
    imine
    0.37
    POSITIVE LOGITS
     closures
    0.41
     ish
    0.39
    }/{
    0.38
    স্তাফিজ
    0.36
     approximation
    0.36
     approximating
    0.35
     neut
    0.35
    Crystal
    0.35
     smoot
    0.35
    ='#
    0.34
    Act Density 0.000%

    No Known Activations