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

    Neuronpedia

    INDEX
    Explanations

    numerals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (selector
    -0.07
     Williamson
    -0.06
    .Services
    -0.06
     startActivityForResult
    -0.06
     TIM
    -0.06
    .list
    -0.06
    .ci
    -0.06
     "\↵
    -0.06
    icro
    -0.06
    をつ
    -0.06
    POSITIVE LOGITS
     Кан
    0.07
    เทศ
    0.06
    奖
    0.06
     recognized
    0.06
    $q
    0.06
    獎
    0.06
     있음
    0.06
    what
    0.06
     What
    0.06
    _Call
    0.06
    Act Density 0.035%

    No Known Activations