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

    Neuronpedia

    INDEX
    Explanations

    code-related commands and instructions that manipulate data or objects

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

    printing and passing arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Stephen
    -0.44
     enfans
    -0.43
    stephen
    -0.42
     onResume
    -0.42
     tendances
    -0.42
     Stephen
    -0.39
     pecados
    -0.39
    omitempty
    -0.39
    PendingIntent
    -0.38
     actes
    -0.38
    POSITIVE LOGITS
     незавершена
    0.65
     ſind
    0.63
    0.62
    Према
    0.58
     мәкал
    0.56
    :✨
    0.56
     дописавши
    0.53
     PagesJaunes
    0.51
     resourceCulture
    0.48
     సౌకర్య
    0.48
    Act Density 0.028%

    No Known Activations