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

    Neuronpedia

    INDEX
    Explanations

    elements of code that define or manipulate data structures and variables in programming

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

    code structures and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.47
     تضيفلها
    -0.46
    ècie
    -0.38
    Yeet
    -0.37
    expandindo
    -0.33
     früh
    -0.33
     viewDidLoad
    -0.32
    hideLoading
    -0.32
     ▶
    -0.32
    TextFormField
    -0.32
    POSITIVE LOGITS
     both
    0.51
    DeleteBehavior
    0.50
     estekak
    0.49
    mbic
    0.49
    both
    0.48
    Personensuche
    0.48
    KommentareTeilen
    0.48
     begge
    0.47
    aarrggbb
    0.46
    afy
    0.46
    Act Density 0.027%

    No Known Activations