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

    Neuronpedia

    INDEX
    Explanations

    the word "that" and related words such as "it" and "what"

    oai_token-act-pair · gemini-2.0-flash

    that

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     that
    -0.91
    webElementGuid
    -0.79
    devamını
    -0.62
    +#+#
    -0.60
    that
    -0.59
    matchCondition
    -0.57
     که
    -0.54
    jsxFileName
    -0.52
    rungsseite
    -0.51
     فريبيس
    -0.51
    POSITIVE LOGITS
     even
    0.74
     даже
    0.67
    even
    0.66
    noinspection
    0.66
     incluso
    0.64
     nawet
    0.64
    Даже
    0.64
     EVEN
    0.63
     навіть
    0.63
     Even
    0.60
    Act Density 1.457%

    No Known Activations