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

    Neuronpedia

    INDEX
    Explanations

    python package installation and setup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     waterfall
    0.40
     freak
    0.40
    benzoimidazol
    0.40
     refinancing
    0.39
     Heinrich
    0.39
     workpiece
    0.39
    zahlung
    0.39
     przyj
    0.39
     archaeologist
    0.39
     wounding
    0.38
    POSITIVE LOGITS
    setup
    0.84
    classifiers
    0.75
     setup
    0.74
     setups
    0.73
    Setup
    0.71
    install
    0.70
    packages
    0.69
     classifiers
    0.69
     install
    0.63
     packages
    0.62
    Act Density 0.005%

    No Known Activations