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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize repetition or returning experiences

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

    never again

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WebVitals
    -0.61
     createSlice
    -0.60
    Rüyada
    -0.59
    ngdoc
    -0.59
    IUrlHelper
    -0.58
    InstrumentedTest
    -0.57
    Derbyniad
    -0.55
    oredCriteria
    -0.55
     AssemblyTitle
    -0.54
    sizeCache
    -0.54
    POSITIVE LOGITS
     jamais
    0.37
     restoration
    0.34
    BackStack
    0.33
    < 
    0.33
     jamás
    0.33
    BatchNorm
    0.32
    結局
    0.32
    ifolium
    0.30
     faſt
    0.29
    ūr
    0.29
    Act Density 0.031%

    No Known Activations