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

    Neuronpedia

    INDEX
    Explanations

    say "a" or "statement"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     університет
    -0.07
     plage
    -0.06
     ещё
    -0.06
     ownership
    -0.06
    Virginia
    -0.06
     wild
    -0.06
    _vector
    -0.06
    ioned
    -0.06
    _abort
    -0.06
    ibly
    -0.06
    POSITIVE LOGITS
     آقای
    0.07
    (each
    0.07
              ↵
    0.07
    FORCE
    0.07
    .PR
    0.06
    -↵
    0.06
    =num
    0.06
     '%$
    0.06
    	k
    0.06
    işleri
    0.06
    Act Density 0.089%

    No Known Activations