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

    Neuronpedia

    INDEX
    Explanations

    quantities and relationships associated with measurements and comparisons

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

    ending in "s"

    np_acts-logits-general · gemini-2.0-flash

    single objects, groups, or occurrences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    素
    -0.37
     relative
    -0.36
    nop
    -0.35
     po
    -0.34
    src
    -0.33
     cre
    -0.32
    edge
    -0.32
     ra
    -0.31
    Relative
    -0.31
     Relative
    -0.31
    POSITIVE LOGITS
    SharedCtor
    0.82
     OFDb
    0.77
    outWeight
    0.71
     disambiguazione
    0.71
     Paglinawan
    0.71
     desmotivaciones
    0.69
     betweenstory
    0.67
     &___
    0.63
    Personendaten
    0.62
    majánló
    0.61
    Act Density 1.012%

    No Known Activations