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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ，因此
    -0.08
    iun
    -0.08
    ábamos
    -0.08
     _:
    -0.08
     densities
    -0.08
     hence
    -0.07
     furthermore
    -0.07
    сли
    -0.07
     además
    -0.07
    .el
    -0.07
    POSITIVE LOGITS
     원하는
    0.09
    _surface
    0.08
     먼저
    0.08
    Surface
    0.08
     размест
    0.08
    _Surface
    0.08
    ासा
    0.08
     gently
    0.08
    _outline
    0.08
     gewünschten
    0.08
    Act Density 0.032%

    No Known Activations