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

    Neuronpedia

    INDEX
    Explanations

    proper nouns referring to people involved in various contexts or incidents

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

    surnames

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſehr
    -0.69
    -0.68
    enterOuterAlt
    -0.68
    [@BOS@]
    -0.68
    <unused16>
    -0.68
    <unused14>
    -0.68
    <unused23>
    -0.68
    <unused28>
    -0.68
    <unused3>
    -0.68
    <unused8>
    -0.68
    POSITIVE LOGITS
     bomberos
    0.39
     vecino
    0.39
     cementerio
    0.38
     enfans
    0.38
    เอง
    0.38
     Nachbarn
    0.37
     abuelo
    0.36
     mediodía
    0.35
     emperador
    0.35
     pasajeros
    0.34
    Act Density 0.061%

    No Known Activations