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

    Neuronpedia

    INDEX
    Explanations

    academic phrases and structural elements in research papers

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

    in specific contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ArgsConstructor
    -0.67
    Javadoc
    -0.65
    الدراسه
    -0.58
     препратки
    -0.57
     spéciales
    -0.57
     financières
    -0.56
    Weblinks
    -0.54
     Вікі
    -0.54
     informée
    -0.53
     Audiodateien
    -0.52
    POSITIVE LOGITS
     Preferencias
    0.66
    ########.
    0.58
    standers
    0.58
    NewRow
    0.56
    InitStruct
    0.55
    ModelAndView
    0.54
    MIDDLEWARE
    0.53
     Pneum
    0.53
     tää
    0.52
    Occup
    0.52
    Act Density 0.378%

    No Known Activations