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

    Neuronpedia

    INDEX
    Explanations

    code structures or expressions involving mathematical operations

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

    Code snippets or table relationships

    np_acts-logits-general · gemini-2.0-flash

    which links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -0.91
    ſchaft
    -0.90
    şört
    -0.90
    niſſe
    -0.84
    ----</
    -0.84
    +#+
    -0.83
    oredCriteria
    -0.82
    enablog
    -0.81
    ThroughAttribute
    -0.81
     ddelwed
    -0.81
    POSITIVE LOGITS
    if
    0.48
    ↵
    0.44
     As
    0.42
    As
    0.40
     if
    0.40
        
    0.39
    $
    0.37
                
    0.37
      
    0.36
     According
    0.36
    Act Density 0.231%

    No Known Activations