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

    Neuronpedia

    INDEX
    Explanations

    reporting

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sax
    -0.08
    튠
    -0.07
     bahçe
    -0.07
     angl
    -0.06
    pu
    -0.06
    佩服
    -0.06
    �
    -0.06
    bach
    -0.06
    离不开
    -0.06
    得天独
    -0.06
    POSITIVE LOGITS
     sentiments
    0.07
    حركات
    0.07
    反應
    0.07
     objects
    0.07
    entropy
    0.07
    Editing
    0.07
    height
    0.07
     Moments
    0.07
    教育培训
    0.07
     Views
    0.07
    Act Density 0.002%

    No Known Activations