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

    Neuronpedia

    INDEX
    Explanations

    already

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    นำ
    -0.06
    .age
    -0.06
     rebut
    -0.06
     mqtt
    -0.06
     detox
    -0.06
    enticated
    -0.06
     teenage
    -0.06
     Nir
    -0.06
    -bot
    -0.06
     pwd
    -0.06
    POSITIVE LOGITS
     vlas
    0.07
     tariffs
    0.07
    (Container
    0.06
     Việt
    0.06
     çift
    0.06
    732
    0.06
     hướng
    0.06
    цент
    0.06
     safeguards
    0.06
    <Character
    0.06
    Act Density 0.022%

    No Known Activations