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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating restrictions or limitations

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

    not limited to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     '\\;'
    -0.52
    Portail
    -0.52
    󠁿
    -0.50
    antMatchers
    -0.49
     مواليد
    -0.48
     مشين
    -0.48
     JpaRepository
    -0.48
    writerow
    -0.47
     Chwiliwch
    -0.47
    ScopeManager
    -0.46
    POSITIVE LOGITS
     best
    0.44
     Mehdi
    0.43
     least
    0.42
    LayoutStyle
    0.42
     resource
    0.41
     Niagara
    0.40
     woll
    0.39
     styled
    0.39
     main
    0.38
     standard
    0.38
    Act Density 0.019%

    No Known Activations