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

    Neuronpedia

    INDEX
    Explanations

    data related to rankings or statistical comparisons

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

    Quantities, especially maximums and minimums

    np_acts-logits-general · gemini-2.0-flash

    highest proportion, lowest concentration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.80
     AssemblyCulture
    -0.79
    AsUp
    -0.77
    PerformLayout
    -0.77
    ंदीखरीदारी
    -0.71
    ########.
    -0.68
    #+#
    -0.66
     nahilalakip
    -0.66
     MainAxisSize
    -0.64
    Personendaten
    -0.64
    POSITIVE LOGITS
     closest
    0.51
     largest
    0.50
     longest
    0.49
     shortest
    0.45
     smallest
    0.42
     warmest
    0.41
     nearest
    0.40
     fewest
    0.39
     highest
    0.39
     broadest
    0.39
    Act Density 0.503%

    No Known Activations