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

    Neuronpedia

    INDEX
    Explanations

    things related to research, statistics or data analysis

    oai_token-act-pair · gemini-2.0-flash

    conditional/contrasting statements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     continúas
    -0.58
     ujednoznacz
    -0.57
     Winaray
    -0.51
    참고
    -0.50
    thing
    -0.50
    сюда
    -0.47
    oton
    -0.46
    ัก
    -0.46
    łaszcza
    -0.45
    gings
    -0.44
    POSITIVE LOGITS
     while
    2.58
    while
    2.28
     whereas
    2.23
     mientras
    2.03
     mentre
    1.98
     whilst
    1.98
     Whereas
    1.97
     WHILE
    1.96
     enquanto
    1.96
    whereas
    1.94
    Act Density 2.586%

    No Known Activations