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

    Neuronpedia

    INDEX
    Explanations

    directory structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pressurized
    0.38
     mobilized
    0.37
     aspirated
    0.35
     Equatorial
    0.35
     sterilized
    0.35
     emprego
    0.35
     implanted
    0.34
     allait
    0.34
     galactose
    0.33
    땃
    0.33
    POSITIVE LOGITS
    README
    1.14
     README
    1.05
    Makefile
    0.91
    Dockerfile
    0.89
    readme
    0.88
    Readme
    0.84
     Makefile
    0.81
     readme
    0.79
    LICENSE
    0.73
    └──
    0.71
    Act Density 0.028%

    No Known Activations