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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and delimiters often used in programming code

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

    UI menu creation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.65
     ioutil
    -0.55
    ſelf
    -0.54
     ſche
    -0.54
    WithIOException
    -0.53
     ſta
    -0.53
     myſelf
    -0.53
     GenerationType
    -0.53
     faſt
    -0.52
     endforeach
    -0.52
    POSITIVE LOGITS
     MenuView
    0.49
     menus
    0.43
     menú
    0.39
     cocinar
    0.38
     PREPARATION
    0.37
     menu
    0.37
     préparation
    0.37
     meal
    0.36
     Sénat
    0.36
     preparar
    0.36
    Act Density 0.000%

    No Known Activations