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

    Neuronpedia

    INDEX
    Explanations

    elements related to the structure and syntax of code, particularly function declarations and object instantiation

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

    Code snippets or fragments

    np_acts-logits-general · gemini-2.0-flash

    code and Polish words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.66
     CreateTagHelper
    -0.52
    úgó
    -0.50
     referrerpolicy
    -0.47
    DJANGO
    -0.46
     crossorigin
    -0.46
    Gruss
    -0.46
    ronpa
    -0.45
     Schw
    -0.45
    autique
    -0.45
    POSITIVE LOGITS
     niż
    0.43
     rather
    0.41
     than
    0.40
    didSet
    0.38
     but
    0.38
    But
    0.36
    rather
    0.36
     But
    0.36
     ogóle
    0.36
    但在
    0.35
    Act Density 0.468%

    No Known Activations