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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    registered trademarks and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    -0.51
     
    -0.47
    .
    -0.37
     and
    -0.37
    >
    -0.35
    -
    -0.34
    </tr>
    -0.34
    ↵
    -0.33
    \
    -0.33
    The
    -0.32
    POSITIVE LOGITS
    Datuak
    0.87
    ⓧ
    0.73
     Numerade
    0.72
     Comprometido
    0.72
    WriteTagHelper
    0.71
     Exacts
    0.69
    ロウィン
    0.68
    transQ
    0.68
    <unused16>
    0.67
    <unused17>
    0.67
    Act Density 0.162%

    No Known Activations