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

    Neuronpedia

    INDEX
    Explanations

    slice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kk
    -0.07
    meno
    -0.07
    fl
    -0.06
    .btnCancel
    -0.06
    possible
    -0.06
     completo
    -0.06
    泼
    -0.06
    .bs
    -0.06
    cono
    -0.06
     detectors
    -0.06
    POSITIVE LOGITS
    python
    0.08
     часть
    0.08
     العراقي
    0.08
    狐
    0.07
    SEQU
    0.07
    �
    0.07
    衡阳
    0.07
    METHOD
    0.07
    🕝
    0.07
     Segment
    0.07
    Act Density 0.004%

    No Known Activations