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

    Neuronpedia

    INDEX
    Explanations

    article excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     RUNNING
    -0.07
     questionable
    -0.07
    北斗
    -0.07
    區
    -0.07
    要把
    -0.07
     wannonce
    -0.07
    levation
    -0.07
     forcing
    -0.07
    _descriptor
    -0.07
    쪄
    -0.06
    POSITIVE LOGITS
    零食
    0.08
     NGOs
    0.08
     capsules
    0.07
     sill
    0.07
    晚饭
    0.07
     blends
    0.07
     Bayer
    0.07
     mins
    0.07
    惯例
    0.07
    cretion
    0.07
    Act Density 0.114%

    No Known Activations