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

    Neuronpedia

    INDEX
    Explanations

    expressions related to common or typical occurrences

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

    common or normal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     prohibido
    -0.46
     venezolano
    -0.45
     Chriftian
    -0.43
     Moscú
    -0.42
     couvercle
    -0.41
     venezol
    -0.40
     Investigaciones
    -0.40
    holdet
    -0.40
     griega
    -0.40
     quirúrg
    -0.40
    POSITIVE LOGITS
     often
    0.71
     frequently
    0.69
     routinely
    0.69
     commonplace
    0.67
     typically
    0.66
     commonly
    0.65
    NameInMap
    0.65
     frequent
    0.64
     typical
    0.61
     common
    0.60
    Act Density 0.028%

    No Known Activations