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

    Neuronpedia

    INDEX
    Explanations

    references to various systems and their components

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

    system or systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ConfigureAwait
    -0.51
    hidupan
    -0.50
     мәгълү
    -0.49
     aparência
    -0.44
    zzleHttp
    -0.43
     fatos
    -0.42
    ffeine
    -0.42
    hadiran
    -0.42
     Maske
    -0.41
     EconPapers
    -0.41
    POSITIVE LOGITS
     system
    0.94
     syste
    0.87
    system
    0.85
     SYSTEM
    0.81
     systeem
    0.80
     sistema
    0.77
     System
    0.77
     systems
    0.76
    System
    0.75
    ystemet
    0.73
    Act Density 0.035%

    No Known Activations