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

    Neuronpedia

    INDEX
    Explanations

    phrases that introduce or reference discussions or thoughts

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

    navigation, on, to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Majefty
    -0.39
    soort
    -0.39
    seende
    -0.37
     tartalomajánló
    -0.35
     ioutil
    -0.34
     évêque
    -0.34
    ſelf
    -0.34
     
    -0.32
    Referencie
    -0.31
     itſelf
    -0.31
    POSITIVE LOGITS
    transQ
    0.73
    0.60
    complexContent
    0.56
    prepareStatement
    0.54
     autorytatywna
    0.52
    urlpatterns
    0.52
    AddTagHelper
    0.52
    ✨:
    0.49
    InputTagHelper
    0.48
    RegressionTest
    0.48
    Act Density 0.001%

    No Known Activations