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

    Neuronpedia

    INDEX
    Explanations

    websites and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     validity
    -0.08
     Unique
    -0.07
     founding
    -0.06
     fyz
    -0.06
     definitive
    -0.06
    _contains
    -0.06
    	format
    -0.06
     <<=
    -0.06
    ()">
    -0.06
    avad
    -0.06
    POSITIVE LOGITS
    739
    0.07
    埋
    0.07
    氣
    0.07
    .schedulers
    0.07
    Qi
    0.06
     vedle
    0.06
     ~~
    0.06
     underscore
    0.06
    oauth
    0.06
    sending
    0.06
    Act Density 0.039%

    No Known Activations