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

    Neuronpedia

    INDEX
    Explanations

    phrases related to statistical models and selection processes

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

    "one" or numbers

    np_acts-logits-general · gemini-2.0-flash

    from one to another

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.52
     instead
    -0.45
    NotFoundError
    -0.43
     invece
    -0.43
     betreft
    -0.42
     matching
    -0.41
    δας
    -0.41
    gesetz
    -0.40
    auti
    -0.40
     jednak
    -0.39
    POSITIVE LOGITS
     one
    1.43
    one
    1.01
     EconPapers
    0.97
     satu
    0.96
     одни
    0.95
     jednej
    0.93
     одной
    0.90
     одного
    0.89
     одном
    0.88
     jednego
    0.87
    Act Density 0.264%

    No Known Activations