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

    Neuronpedia

    INDEX
    Explanations

    the words "this" and "that" where they are used to refer to math concepts

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    è¿Ļ个
    -0.08
     ones
    -0.07
    -this
    -0.07
    ysz
    -0.07
    orus
    -0.06
    this
    -0.06
     this
    -0.06
    è¿ĻäºĽ
    -0.06
    è¿Ļ
    -0.06
    NOP
    -0.06
    POSITIVE LOGITS
    uteur
    0.08
    erno
    0.07
    ched
    0.07
    ssue
    0.07
    ladu
    0.06
    quence
    0.06
    OrNil
    0.06
    ẫ
    0.06
    SqlParameter
    0.06
    ero
    0.06
    Act Density 0.222%

    No Known Activations