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

    Neuronpedia

    INDEX
    Explanations

    mathematical operations and expressions

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

    Numbers followed by arithmetic symbols

    np_acts-logits-general · gemini-2.0-flash

    math equations and calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.76
     (
    -0.55
     a
    -0.54
    ↵
    -0.53
      
    -0.53
    ↵↵
    -0.52
     The
    -0.52
     the
    -0.49
    흔
    -0.48
    ,
    -0.47
    POSITIVE LOGITS
    AndEndTag
    1.20
    expandindo
    1.11
    IntoConstraints
    1.06
    ConstraintMaker
    1.00
    reportWebVitals
    0.98
     ſever
    0.96
    存于互联网档案馆
    0.94
     ſtate
    0.94
    TintMode
    0.94
    HomeAsUpEnabled
    0.93
    Act Density 2.059%

    No Known Activations