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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate challenges or difficulties in specific situations

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

    Sentences that start with coordinating conjunctions

    np_acts-logits-general · gemini-2.0-flash

    recommendations vs outdated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ange
    -0.41
    ParallelGroup
    -0.39
     Mapper
    -0.38
    Становништво
    -0.37
     nun
    -0.34
    kern
    -0.33
     pompe
    -0.33
     nave
    -0.32
     agora
    -0.32
     arist
    -0.31
    POSITIVE LOGITS
     &___
    0.66
     AssemblyCompany
    0.56
    expandindo
    0.54
     صوتيه
    0.54
     propOrder
    0.53
     Picchu
    0.50
    ########.
    0.49
     NSCoder
    0.48
    ArrowToggle
    0.48
     AssemblyProduct
    0.47
    Act Density 0.452%

    No Known Activations