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

    Neuronpedia

    INDEX
    Explanations

    lists of numbers and phone numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     言っ
    0.45
    lyPlugin
    0.36
     入っ
    0.35
    𒌦
    0.35
    adType
    0.34
    QTTR
    0.34
    此同时
    0.34
    𒁕
    0.34
    <unused288>
    0.34
    THz
    0.33
    POSITIVE LOGITS
    -
    0.40
    _
    0.35
    –
    0.34
     of
    0.33
    <start_of_image>
    0.31
    \_
    0.30
    ​
    0.30
    of
    0.30
    ’
    0.30
    mj
    0.29
    Act Density 0.201%

    No Known Activations