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

    Neuronpedia

    INDEX
    Explanations

    Python libraries and packages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     DCs
    0.85
     disgust
    0.83
     irritation
    0.83
     froth
    0.80
     irrit
    0.80
     bodily
    0.78
     ail
    0.76
     frowning
    0.76
     molar
    0.75
     patern
    0.75
    POSITIVE LOGITS
    lib
    1.22
    Lib
    1.12
    库
    1.12
    软件包
    1.08
    plotlib
    1.06
    parser
    1.05
    开源
    1.03
    kit
    1.03
    okit
    1.01
    SDK
    1.01
    Act Density 0.233%

    No Known Activations