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

    Neuronpedia

    INDEX
    Explanations

    sentences that contain the words "that" or "think".

    oai_token-act-pair · gemini-2.0-flash

    that

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     EconPapers
    -1.05
     Either
    -0.88
    Even
    -0.85
    TypedDataSet
    -0.84
     Even
    -0.84
     AssemblyProduct
    -0.84
     Neither
    -0.84
     مشين
    -0.82
     When
    -0.82
     Regardless
    -0.81
    POSITIVE LOGITS
    ’
    0.71
    '
    0.65
     is
    0.39
    lungen
    0.38
    kuu
    0.37
     гг
    0.37
    ´
    0.36
    Referințe
    0.34
     by
    0.33
     Leroy
    0.33
    Act Density 10.566%

    No Known Activations