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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    velt
    -0.07
     müş
    -0.06
     Sabbath
    -0.06
    ètre
    -0.06
     삼성
    -0.06
    _booking
    -0.06
     DEL
    -0.06
    datatable
    -0.06
     인천
    -0.06
    вердж
    -0.06
    POSITIVE LOGITS
     nastav
    0.06
    redirect
    0.06
     Universal
    0.06
    سان
    0.06
     Brewery
    0.06
     overd
    0.06
     algorithm
    0.06
     relevant
    0.06
     independently
    0.06
     positive
    0.06
    Act Density 0.058%

    No Known Activations