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

    Neuronpedia

    INDEX
    Explanations

    references to community centers and related facilities

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

    community centers and club houses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    xtick
    -0.35
     Dhabi
    -0.32
    Encyklopedia
    -0.31
     引
    -0.31
    gesteld
    -0.30
     kompon
    -0.30
     подраз
    -0.30
     kaynağından
    -0.30
    Zitat
    -0.29
     thèse
    -0.28
    POSITIVE LOGITS
     houſe
    0.75
     Houſe
    0.73
     gymnasium
    0.66
     uſed
    0.65
     Biôgrafia
    0.63
     ſta
    0.63
     clubhouse
    0.62
    MLLoader
    0.62
    ſelf
    0.60
    ſelves
    0.57
    Act Density 0.016%

    No Known Activations