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

    Neuronpedia

    INDEX
    Explanations

    say "L" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ุ์
    -0.07
     vbox
    -0.06
    dera
    -0.06
    _rectangle
    -0.06
    니까
    -0.06
    (chain
    -0.06
     변경
    -0.06
     GL
    -0.06
     Kund
    -0.06
     обуч
    -0.06
    POSITIVE LOGITS
    987
    0.07
     ті
    0.07
    =f
    0.06
    .=
    0.06
     فه
    0.06
    ۱۹
    0.06
     feminism
    0.06
     advances
    0.06
    03
    0.06
    PushButton
    0.06
    Act Density 0.000%

    No Known Activations