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

    Neuronpedia

    INDEX
    Explanations

    references to directory structures and folder organization

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

    File paths or directory names

    np_acts-logits-general · gemini-2.0-flash

    folder and directory creation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.74
    üyada
    -0.59
    igenschaften
    -0.53
     nonatomic
    -0.48
    }{*}{
    -0.48
    Демографія
    -0.48
    soort
    -0.48
     pianta
    -0.48
    >--}}
    -0.47
     indisponible
    -0.47
    POSITIVE LOGITS
     folder
    0.87
     mkdir
    0.85
    mkdir
    0.83
     folders
    0.80
     Folder
    0.74
    folder
    0.67
    文件夹
    0.67
    フォル
    0.64
     directory
    0.62
    Folder
    0.61
    Act Density 0.354%

    No Known Activations