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

    Neuronpedia

    INDEX
    Explanations

    tabular data structures and their specifications

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

    tabular data delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.88
    MLLoader
    -0.88
    ⤹
    -0.85
     queſta
    -0.83
    ScopeManager
    -0.82
     beſte
    -0.81
    <unused41>
    -0.80
    ﹧
    -0.80
    [@BOS@]
    -0.80
    <unused8>
    -0.80
    POSITIVE LOGITS
     
    0.38
    I
    0.35
     total
    0.34
    ,
    0.31
    ↵↵
    0.31
      
    0.29
    )
    0.28
    P
    0.28
    ..
    0.28
    #
    0.27
    Act Density 0.138%

    No Known Activations