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

    Neuronpedia

    INDEX
    Explanations

    the word "during" and sometimes finds the word "speed"

    oai_token-act-pair · gemini-2.0-flash

    during

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     during
    -1.77
    during
    -1.61
     DURING
    -1.46
     durante
    -1.37
     During
    -1.29
     tijdens
    -1.24
    During
    -1.20
     ujednoznacz
    -1.20
     kasarigan
    -1.14
    durante
    -1.13
    POSITIVE LOGITS
    n
    0.80
    a
    0.76
    m
    0.75
    p
    0.75
     
    0.73
    com
    0.73
    2
    0.73
    h
    0.73
    y
    0.69
    “
    0.68
    Act Density 1.408%

    No Known Activations