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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Pod
    -0.07
    message
    -0.06
     ±
    -0.06
     trẻ
    -0.06
     Mezi
    -0.06
     baskı
    -0.06
    [user
    -0.06
     Cover
    -0.06
     ben
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    illaume
    0.07
     kayı
    0.07
     ornament
    0.07
    ΩΣ
    0.07
    (robot
    0.06
     GAM
    0.06
    erro
    0.06
    woord
    0.06
    ISH
    0.06
     odmít
    0.06
    Act Density 0.012%

    No Known Activations