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

    Neuronpedia

    INDEX
    Explanations

    Interview questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    о�
    -0.07
    λόγ
    -0.06
     rode
    -0.06
     gi�
    -0.06
    .loss
    -0.06
     특별
    -0.06
    .Selenium
    -0.06
    nom
    -0.06
    ког
    -0.06
     sandy
    -0.06
    POSITIVE LOGITS
     Painter
    0.07
     дум
    0.07
    alli
    0.06
    으
    0.06
     god
    0.06
    所属
    0.06
    PLIER
    0.06
     doctrine
    0.06
    (targetEntity
    0.06
    ceptions
    0.06
    Act Density 0.030%

    No Known Activations