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

    Neuronpedia

    INDEX
    Explanations

    II

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hay
    -0.07
    trash
    -0.06
    आर
    -0.06
    Center
    -0.06
     salir
    -0.06
    constructor
    -0.06
     Ş
    -0.06
     zer
    -0.06
     πρώτη
    -0.06
     desper
    -0.06
    POSITIVE LOGITS
     WWII
    0.08
     Developed
    0.07
    elopment
    0.07
    ­i
    0.07
     {}\
    0.06
    _START
    0.06
    _pix
    0.06
     evacuated
    0.06
     Stocks
    0.06
     temporarily
    0.06
    Act Density 0.006%

    No Known Activations