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

    Neuronpedia

    INDEX
    Explanations

    rainbow/bows

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sheep
    -0.07
     myš
    -0.07
     Daw
    -0.07
     disguised
    -0.07
     Evel
    -0.07
    PushMatrix
    -0.06
     UIP
    -0.06
    Lane
    -0.06
     درد
    -0.06
    偷
    -0.06
    POSITIVE LOGITS
    .Lib
    0.07
    iв
    0.07
     #"
    0.06
    تب
    0.06
     Indoor
    0.06
     финансов
    0.06
    ьер
    0.06
    (REG
    0.06
    ittle
    0.06
    comic
    0.06
    Act Density 0.001%

    No Known Activations