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

    Neuronpedia

    INDEX
    Explanations

    -I

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mates
    -0.07
    Б
    -0.06
     convin
    -0.06
    .ByteArray
    -0.06
    monkey
    -0.06
    ليل
    -0.06
     publishes
    -0.06
    _representation
    -0.06
     annotation
    -0.06
     lions
    -0.06
    POSITIVE LOGITS
     vigor
    0.08
     etmek
    0.07
    429
    0.07
    (^
    0.07
    formerly
    0.07
    urnished
    0.06
    vy
    0.06
     wife
    0.06
    (str
    0.06
     Newly
    0.06
    Act Density 0.000%

    No Known Activations