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

    Neuronpedia

    INDEX
    Explanations

    button

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    edl
    -0.07
    alignment
    -0.07
     Equivalent
    -0.06
    CategoryId
    -0.06
    -digit
    -0.06
    -selection
    -0.06
    eut
    -0.06
    _placement
    -0.06
    DataContext
    -0.06
    植
    -0.06
    POSITIVE LOGITS
     biraz
    0.06
    ensa
    0.06
    ，就
    0.06
    allowed
    0.06
     payday
    0.06
     připoj
    0.06
    etros
    0.06
    _vals
    0.06
    -monitor
    0.06
    SECRET
    0.06
    Act Density 0.019%

    No Known Activations