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

    Neuronpedia

    INDEX
    Explanations

    programming or algorithmic constructs related to data manipulation

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

    Mathematical or programming code snippets

    np_acts-logits-general · gemini-2.0-flash

    mathematical symbols and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.92
    ########.
    -0.87
    parsedMessage
    -0.79
     Menſchen
    -0.76
     queſta
    -0.75
     erſten
    -0.75
    iſchen
    -0.74
    <unused79>
    -0.74
    <unused52>
    -0.74
    <unused28>
    -0.74
    POSITIVE LOGITS
     poj
    0.30
     abruptly
    0.26
     empty
    0.25
     ilg
    0.24
     получи
    0.24
     senere
    0.23
     snapped
    0.23
    หว่าง
    0.22
     suddenly
    0.21
     due
    0.21
    Act Density 0.448%

    No Known Activations