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

    Neuronpedia

    INDEX
    Explanations

    key terms and phrases in various languages

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

    drag rope

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tembelea
    -0.49
    antMatchers
    -0.42
     manguera
    -0.40
     ***!
    -0.39
    RegistryLite
    -0.37
    Välislingid
    -0.36
    .*")]
    -0.35
     financiación
    -0.34
     aislamiento
    -0.34
     usarlo
    -0.34
    POSITIVE LOGITS
    最快更新
    0.57
     $_"
    0.54
    <?,
    0.52
     $_(
    0.48
    GTCX
    0.47
     hanem
    0.47
     GenerationType
    0.47
     vrijwilli
    0.45
     createdBy
    0.44
    balleur
    0.43
    Act Density 0.001%

    No Known Activations