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

    Neuronpedia

    INDEX
    Explanations

    Machine learning model training

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ican
    -0.07
    .BOTTOM
    -0.06
     settlers
    -0.06
     ensuite
    -0.06
     degraded
    -0.06
     khắc
    -0.06
     Vulcan
    -0.06
     guar
    -0.06
     tolerant
    -0.06
    _Window
    -0.06
    POSITIVE LOGITS
    Noise
    0.07
    ласти
    0.06
     Approximately
    0.06
    .cy
    0.06
     Guest
    0.06
     عاما
    0.06
     informative
    0.06
     Kem
    0.06
    主义
    0.06
     обязан
    0.06
    Act Density 0.019%

    No Known Activations