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

    Neuronpedia

    INDEX
    Explanations

    listing components and requirements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     үч
    0.39
     ਇੱਕ
    0.36
    ్రీన్
    0.34
     زیرمه
    0.32
     ఓ
    0.32
     विद्यु
    0.32
     SAVE
    0.32
     ሁለት
    0.32
     tubig
    0.32
     ఒక
    0.31
    POSITIVE LOGITS
     and
    0.47
    /
    0.42
    或其他
    0.40
     و
    0.40
     for
    0.38
    和其他
    0.37
     மற்றும்
    0.35
    hu
    0.35
     वगैरह
    0.35
    huana
    0.34
    Act Density 0.202%

    No Known Activations