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

    Neuronpedia

    INDEX
    Explanations

    car engines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (delay
    -0.07
     Windows
    -0.07
    .clip
    -0.07
     Probability
    -0.06
    Ø
    -0.06
    Roger
    -0.06
     dealer
    -0.06
     Lust
    -0.06
    .scenes
    -0.06
     fans
    -0.06
    POSITIVE LOGITS
    -of
    0.07
    endtime
    0.06
    .of
    0.06
    eceğiz
    0.06
    ola
    0.06
    orget
    0.06
    @Test
    0.06
     xhttp
    0.06
    ोल
    0.06
     düzey
    0.06
    Act Density 0.015%

    No Known Activations