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

    Neuronpedia

    INDEX
    Explanations

    quantitative descriptors related to amounts or quantities

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

    greatest quantities or highest degree

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    躇
    -0.54
     CURIAM
    -0.52
     sánchez
    -0.50
     informée
    -0.50
     bø
    -0.46
    meneu
    -0.46
    acinth
    -0.46
    IZONTAL
    -0.46
    duled
    -0.45
    Projek
    -0.44
    POSITIVE LOGITS
     가장
    1.16
     самое
    1.13
     most
    1.13
     best
    1.05
    most
    1.02
     Most
    1.01
     самых
    1.01
     самые
    1.01
     सबसे
    1.01
     biggest
    1.00
    Act Density 0.004%

    No Known Activations