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

    Neuronpedia

    INDEX
    Explanations

    number

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     infix
    -0.07
    ialized
    -0.06
     MyApp
    -0.06
     разв
    -0.06
     बद
    -0.06
     ومن
    -0.06
     booked
    -0.06
    _Up
    -0.06
     appeals
    -0.06
    _Message
    -0.06
    POSITIVE LOGITS
     number
    0.08
     количе
    0.07
    nbr
    0.07
     neut
    0.07
     кіль
    0.07
     commodo
    0.07
    __
    0.07
     understandably
    0.07
    zahl
    0.07
     {//
    0.07
    Act Density 0.061%

    No Known Activations