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

    Neuronpedia

    INDEX
    Explanations

    references to directory structures and file management concepts

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

    root directory paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InputTagHelper
    -0.60
    RTEE
    -0.57
     InkWell
    -0.55
    قایناق‌لار
    -0.54
    andExpect
    -0.54
    ыгана
    -0.50
    expandindo
    -0.48
    PMailer
    -0.47
    Хьажоргаш
    -0.47
     ویکی‌پدیا
    -0.46
    POSITIVE LOGITS
     root
    1.05
    root
    0.98
    Root
    0.96
     Root
    0.92
     raíz
    0.83
     raiz
    0.80
     roots
    0.79
     ROOT
    0.77
    ROOT
    0.76
     racines
    0.74
    Act Density 0.008%

    No Known Activations