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

    Neuronpedia

    INDEX
    Explanations

    text related to software updates and new features

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    laughter
    -0.06
    undler
    -0.06
     @$_
    -0.06
     suddenly
    -0.06
    REE
    -0.06
     dev
    -0.06
    modify
    -0.06
     vir
    -0.06
    (Resources
    -0.06
    276
    -0.05
    POSITIVE LOGITS
     improvements
    0.10
     minor
    0.10
     improved
    0.10
    minor
    0.09
     fixes
    0.09
     Minor
    0.09
     improves
    0.09
     miscellaneous
    0.08
    Minor
    0.08
     bug
    0.08
    Act Density 0.018%

    No Known Activations