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

    Neuronpedia

    INDEX
    Explanations

    efficacy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ела
    -0.06
     noise
    -0.06
     delays
    -0.06
    /swagger
    -0.06
    TRAN
    -0.06
    érie
    -0.06
    -offs
    -0.06
     mong
    -0.06
    _STARTED
    -0.06
    UEL
    -0.06
    POSITIVE LOGITS
     blossom
    0.07
     Juda
    0.07
     약
    0.07
    방송
    0.07
     трех
    0.07
     Từ
    0.06
     Bilim
    0.06
     Rom
    0.06
     Indones
    0.06
    URLConnection
    0.06
    Act Density 0.031%

    No Known Activations