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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and specific names related to individuals or entities

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

    prefix + suffix compounds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused28>
    -0.91
    <unused52>
    -0.91
    <unused41>
    -0.91
    <unused47>
    -0.91
    <unused74>
    -0.91
    [@BOS@]
    -0.91
    <unused51>
    -0.91
    <unused79>
    -0.91
    <unused3>
    -0.90
    <unused8>
    -0.90
    POSITIVE LOGITS
     Grecs
    0.40
     hoved
    0.33
     enfans
    0.31
     sagrado
    0.31
    -
    0.29
     presentada
    0.29
     contemporáneo
    0.29
     venezolano
    0.29
     pierres
    0.28
     deportivos
    0.28
    Act Density 0.075%

    No Known Activations