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

    Neuronpedia

    INDEX
    Explanations

    instances of dialogue or remarks made by characters

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

    Attribution of speech or thought

    np_acts-logits-general · gemini-2.0-flash

    speaking or writing observations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ReactDOM
    -0.49
    Heres
    -0.49
     Suivez
    -0.48
    DockStyle
    -0.47
    Gambas
    -0.46
     Encyclopaedia
    -0.46
     sauvage
    -0.45
     Вікі
    -0.44
     verità
    -0.44
    EntityFramework
    -0.44
    POSITIVE LOGITS
     remark
    1.17
     comment
    1.15
     commented
    1.14
     remarked
    1.13
     commenting
    1.06
     Comment
    0.98
    commented
    0.96
     COMMENT
    0.94
    comment
    0.92
     noting
    0.89
    Act Density 0.268%

    No Known Activations