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

    Neuronpedia

    INDEX
    Explanations

    MA

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vocabulary
    -0.08
    เสม
    -0.08
    Handler
    -0.08
    .today
    -0.07
    .rdf
    -0.07
     sky
    -0.07
    .Memory
    -0.07
    SuppressWarnings
    -0.07
     mountain
    -0.07
    Detector
    -0.07
    POSITIVE LOGITS
    _PS
    0.08
    _receive
    0.07
     Stadt
    0.07
     клуб
    0.07
    aul
    0.07
    保利
    0.07
    윗
    0.07
    _gc
    0.07
    ɸ
    0.07
    麗
    0.07
    Act Density 0.000%

    No Known Activations