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

    Neuronpedia

    INDEX
    Explanations

    mathematical formulas or expressions involving fractions and variables

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

    mathematical fractions and indices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.75
     vPvB
    -0.58
    NameInMap
    -0.52
     mues
    -0.52
    الحياه
    -0.51
     BIBSYS
    -0.51
    chieht
    -0.50
    AddTagHelper
    -0.50
     queſta
    -0.49
     spray
    -0.48
    POSITIVE LOGITS
    }{
    0.77
    )}{
    0.57
    }}}{
    0.55
     orilla
    0.53
    }}{
    0.52
    }{\
    0.50
     }}}{
    0.49
    )}}{
    0.49
     Utilizamos
    0.48
     }{
    0.47
    Act Density 0.081%

    No Known Activations