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

    Neuronpedia

    INDEX
    Explanations

    various formatting elements and special characters in text

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

    span style

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
      
    -0.39
     
    -0.34
    /
    -0.34
    ,
    -0.32
    The
    -0.32
    A
    -0.32
    ↵
    -0.31
    .
    -0.30
     once
    -0.30
    2
    -0.29
    POSITIVE LOGITS
     surla
    0.96
    <unused28>
    0.96
    <unused43>
    0.96
    <unused41>
    0.96
    <unused51>
    0.96
    <unused52>
    0.96
    [@BOS@]
    0.96
    <unused79>
    0.96
    <unused23>
    0.96
    <unused17>
    0.96
    Act Density 0.004%

    No Known Activations