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

    Neuronpedia

    INDEX
    Explanations

    expressions of excitement or delight

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

    spoken quotes attributed to speakers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     versteht
    -0.32
     daardoor
    -0.28
     paljon
    -0.28
     לפ
    -0.28
     unzip
    -0.28
     alcool
    -0.28
    understood
    -0.28
    ZB
    -0.28
     zipped
    -0.27
     vielfach
    -0.27
    POSITIVE LOGITS
    ScopeManager
    0.75
    Diwedd
    0.74
     pleaſure
    0.66
    󠁴
    0.64
    MemoryWarning
    0.63
     Roskov
    0.62
    contentLoaded
    0.61
    waitKey
    0.60
    hoeddwyd
    0.59
    RTGC
    0.58
    Act Density 0.140%

    No Known Activations