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

    Neuronpedia

    INDEX
    Explanations

    references to legal and governmental terms and entities

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

    World War I, II, and similar historical events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vandens
    -0.38
     amenazas
    -0.35
     rodillas
    -0.32
     ziyaret
    -0.32
     ejemplares
    -0.32
     amenaza
    -0.31
     vzduchu
    -0.30
     jums
    -0.30
     regalías
    -0.30
     oídos
    -0.29
    POSITIVE LOGITS
     queſta
    1.04
     betweenstory
    0.98
    <unused28>
    0.93
    [@BOS@]
    0.93
    <unused8>
    0.93
    <unused17>
    0.93
    <unused41>
    0.93
    <unused16>
    0.93
    <pad>
    0.93
    <unused14>
    0.93
    Act Density 0.310%

    No Known Activations