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

    Neuronpedia

    INDEX
    Explanations

    phrases describing comparisons or differences between entities

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

    in a specific context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     between
    -1.22
    Between
    -1.10
     Between
    -1.08
    between
    -1.06
     BETWEEN
    -1.00
     между
    -0.95
     zwischen
    -0.88
     tussen
    -0.86
     між
    -0.85
     mellan
    -0.85
    POSITIVE LOGITS
     autorytatywna
    0.82
     nakalista
    0.73
    mybatisplus
    0.66
     Normdatei
    0.65
    addCriterion
    0.62
     OMITBAD
    0.60
    setVerticalGroup
    0.60
    rungsseite
    0.59
    ագրություններ
    0.59
     ffilmiau
    0.59
    Act Density 0.169%

    No Known Activations