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

    Neuronpedia

    INDEX
    Explanations

    code or technical implementations and methodologies

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

    Solutions, methods, or approaches to problems

    np_acts-logits-general · gemini-2.0-flash

    method or approach

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    çek
    -0.70
    parsedMessage
    -0.69
    HostException
    -0.67
     EconPapers
    -0.67
    '])->
    -0.64
    ImageContext
    -0.59
    RetentionPolicy
    -0.58
     MainAxisSize
    -0.57
    dafx
    -0.55
    MIDDLEWARE
    -0.55
    POSITIVE LOGITS
     method
    0.83
     methode
    0.74
     technique
    0.74
     méthode
    0.72
     methods
    0.72
     metode
    0.72
     approaches
    0.71
    method
    0.71
     méthodes
    0.70
    elegant
    0.70
    Act Density 0.915%

    No Known Activations