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

    Neuronpedia

    INDEX
    Explanations

    essay/article text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     glance
    -0.07
     jed
    -0.06
     glColor
    -0.06
    ...'
    -0.06
     dicho
    -0.06
    -site
    -0.06
     İh
    -0.06
    ]];
    -0.06
    "All
    -0.06
    ########################################################
    -0.06
    POSITIVE LOGITS
     bombing
    0.07
    extent
    0.07
    705
    0.06
    opic
    0.06
    513
    0.06
     kart
    0.06
     developmental
    0.06
    rium
    0.06
    تری
    0.06
     nhiễm
    0.06
    Act Density 0.016%

    No Known Activations