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

    Neuronpedia

    INDEX
    Explanations

    Cup

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gaussian
    -0.06
    entral
    -0.06
    사가
    -0.06
    eneg
    -0.06
     wield
    -0.06
     frequency
    -0.06
     gaze
    -0.06
    ruitment
    -0.06
     ranks
    -0.06
     Attached
    -0.06
    POSITIVE LOGITS
    .cb
    0.07
     çal
    0.06
    .labelControl
    0.06
    言葉
    0.06
    successfully
    0.06
    _forum
    0.06
    ्रश
    0.06
    -connect
    0.06
     اروپ
    0.06
     dnes
    0.06
    Act Density 0.002%

    No Known Activations