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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     expérience
    -0.07
    итив
    -0.07
    .Foundation
    -0.07
     ux
    -0.07
    ãy
    -0.07
     Fox
    -0.06
    938
    -0.06
     آغاز
    -0.06
     پاد
    -0.06
     اعمال
    -0.06
    POSITIVE LOGITS
     +=↵
    0.07
     Syrians
    0.07
     Howell
    0.07
    (Source
    0.06
     fearing
    0.06
    工業
    0.06
    -save
    0.06
     YELLOW
    0.06
    (TokenType
    0.06
    Để
    0.06
    Act Density 0.003%

    No Known Activations