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

    Neuronpedia

    INDEX
    Explanations

    Pubs and hotels

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .substr
    -0.07
    ]\
    -0.06
     визнача
    -0.06
     glUniform
    -0.06
    (K
    -0.06
     butterflies
    -0.05
    カ
    -0.05
     человек
    -0.05
    .configure
    -0.05
     assault
    -0.05
    POSITIVE LOGITS
     Coco
    0.07
    leneck
    0.07
     strips
    0.06
     زنده
    0.06
    _soft
    0.06
    بي
    0.06
     Indian
    0.06
     Keeping
    0.06
     plate
    0.06
    drFc
    0.06
    Act Density 0.047%

    No Known Activations