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

    Neuronpedia

    INDEX
    Explanations

    XML and HTML tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    र
    1.41
     beheld
    1.22
    ر
    1.21
    "\
    1.17
     dove
    1.16
    ្នក
    1.15
     inflicted
    1.15
     заболеваний
    1.14
     bestowed
    1.13
    1.12
    POSITIVE LOGITS
    ו
    1.50
    et
    1.30
    o
    1.26
    on
    1.24
    s
    1.17
    ে
    1.12
    eof
    1.09
    >′
    1.08
    sess
    1.08
    cstring
    1.06
    Act Density 0.032%

    No Known Activations