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

    Neuronpedia

    INDEX
    Explanations

    numerical references or identifiers associated with names, likely related to genealogy or historical figures

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

    historical figures and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Datuak
    -0.80
    aarrggbb
    -0.79
     للمعارف
    -0.79
     transfieras
    -0.76
    <unused41>
    -0.74
    <unused28>
    -0.74
    <unused17>
    -0.74
    <unused52>
    -0.74
    <unused8>
    -0.74
    [@BOS@]
    -0.74
    POSITIVE LOGITS
     siècles
    0.38
     térm
    0.33
     vinto
    0.32
    <eos>
    0.32
     réforme
    0.31
     quirúrg
    0.30
     bencana
    0.30
     collectivités
    0.30
     vē
    0.30
     roble
    0.29
    Act Density 0.026%

    No Known Activations