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

    Neuronpedia

    INDEX
    Explanations

    Link

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     statue
    -0.08
     普
    -0.08
     Brand
    -0.08
    featured
    -0.07
     monument
    -0.07
    Featured
    -0.07
    ワ
    -0.07
    ាត់
    -0.07
    blings
    -0.07
     muted
    -0.07
    POSITIVE LOGITS
    -level
    0.11
    层
    0.11
     স্ত
    0.10
     layer
    0.10
     स्तर
    0.10
     Layer
    0.10
    _layer
    0.09
     பகுதியில்
    0.09
    -layer
    0.09
    ရေး
    0.09
    Act Density 0.003%

    No Known Activations