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

    Neuronpedia

    INDEX
    Explanations

    specific LaTeX formatting and structural elements in mathematical or scientific texts

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

    Mathematical/scientific notation and symbols

    np_acts-logits-general · gemini-2.0-flash

    code snippets and file paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tunn
    -0.49
    tschafts
    -0.49
    🏻
    -0.48
    americas
    -0.45
    rawd
    -0.44
    erals
    -0.44
    wark
    -0.43
     odkazy
    -0.42
     renseignements
    -0.42
    ophosph
    -0.41
    POSITIVE LOGITS
     للاسماء
    0.96
     @"/
    0.94
    IsContent
    0.92
    ValueStyle
    0.88
     оригіналу
    0.86
    AddTagHelper
    0.86
    CloseOperation
    0.81
     beginnetje
    0.80
    ]")]
    0.77
    GIVEREF
    0.76
    Act Density 0.011%

    No Known Activations