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

    Neuronpedia

    INDEX
    Explanations

    main

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fy
    -0.07
     fearful
    -0.07
     Bek
    -0.07
     比
    -0.07
    ocr
    -0.07
    Pick
    -0.07
     Pero
    -0.07
    _deposit
    -0.06
    ventory
    -0.06
    dera
    -0.06
    POSITIVE LOGITS
     main
    0.13
     Main
    0.12
    main
    0.10
     основ
    0.10
    Main
    0.09
     mains
    0.09
    .main
    0.09
     Maine
    0.08
    /main
    0.08
     глав
    0.08
    Act Density 0.040%

    No Known Activations