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

    Neuronpedia

    INDEX
    Explanations

    quality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     чоловік
    -0.07
    Sam
    -0.07
    layarak
    -0.07
    fidf
    -0.07
     فهم
    -0.07
     insanın
    -0.06
     вб
    -0.06
    (timer
    -0.06
     dosud
    -0.06
     cavern
    -0.06
    POSITIVE LOGITS
     quality
    0.20
     Quality
    0.18
    Quality
    0.16
     qualities
    0.14
    -quality
    0.11
    quality
    0.10
    质量
    0.09
    _quality
    0.09
    .quality
    0.09
    qualities
    0.09
    Act Density 0.042%

    No Known Activations