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

    Neuronpedia

    INDEX
    Explanations

    100

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    лекс
    -0.07
    Lu
    -0.07
    ун
    -0.06
     trưởng
    -0.06
    Cont
    -0.06
     Dane
    -0.06
     Promotion
    -0.06
    GM
    -0.06
    Prev
    -0.06
    Fri
    -0.06
    POSITIVE LOGITS
     Immutable
    0.07
     Undo
    0.06
     gratuit
    0.06
     {}.
    0.06
    (Mouse
    0.06
    .constant
    0.06
     disliked
    0.06
    /top
    0.06
     Come
    0.06
     docker
    0.06
    Act Density 0.010%

    No Known Activations