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

    Neuronpedia

    INDEX
    Explanations

    denies / negating / negación

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    。</
    1.18
    。
    1.17
    ۔
    1.09
     ПРО
    1.04
    ü
    1.03
     دي
    1.02
     നിങ്ങൾ
    1.02
     can
    1.01
    Ни
    1.01
     crucified
    1.00
    POSITIVE LOGITS
    s
    1.35
    et
    1.34
    d
    1.33
    appropriate
    1.31
     and
    1.30
    at
    1.26
    การ
    1.21
    6
    1.20
    able
    1.17
    ed
    1.16
    Act Density 0.000%

    No Known Activations