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

    Neuronpedia

    INDEX
    Explanations

    who followed by a verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     which
    1.21
     ktoré
    1.11
     are
    1.09
     assassins
    1.07
    which
    1.05
    they
    1.05
     ordinal
    1.03
     somebody
    1.02
     které
    1.01
     often
    1.00
    POSITIVE LOGITS
    л
    1.45
    ه
    1.36
    ة
    1.15
    o
    1.15
    os
    1.08
    ed
    1.04
    oq
    0.99
    ሳት
    0.98
    ו
    0.97
    ériment
    0.96
    Act Density 0.067%

    No Known Activations