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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (cx
    -0.06
     правиль
    -0.05
    _results
    -0.05
    isiyle
    -0.05
    看见
    -0.05
     Reno
    -0.05
     painting
    -0.05
     страш
    -0.05
     traces
    -0.05
     pname
    -0.05
    POSITIVE LOGITS
     To
    0.08
     TO
    0.08
     to
    0.08
     Ka
    0.08
     objectMapper
    0.07
    .shift
    0.07
    :H
    0.07
    kategori
    0.07
    мин
    0.07
    &action
    0.07
    Act Density 0.008%

    No Known Activations