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

    Neuronpedia

    INDEX
    Explanations

    specific reference words related to numbers and entities in mathematical contexts

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

    the second, the common

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    kurat
    -0.31
     tuttavia
    -0.29
     dragen
    -0.29
     Infatti
    -0.29
     navnet
    -0.28
    物
    -0.28
     eneste
    -0.27
     انه
    -0.27
     أنه
    -0.27
     infatti
    -0.27
    POSITIVE LOGITS
    expandindo
    0.79
    <unused52>
    0.78
    <unused74>
    0.77
    <unused23>
    0.77
    <unused41>
    0.77
    <unused14>
    0.77
    <unused16>
    0.77
    <unused8>
    0.77
    [@BOS@]
    0.77
    <unused3>
    0.77
    Act Density 0.000%

    No Known Activations