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

    Neuronpedia

    INDEX
    Explanations

    referenced academic citations and their associated details

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

    econometric theory

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }$.
    -0.30
       
    -0.29
     E
    -0.29
    }`).
    -0.29
     Metzger
    -0.28
     żeby
    -0.28
     võ
    -0.28
    Yes
    -0.28
     Yes
    -0.27
     extérieure
    -0.27
    POSITIVE LOGITS
    Geplaatst
    0.89
    ReusableCell
    0.86
     kasarigan
    0.84
    tagHelperRunner
    0.77
    MLLoader
    0.73
     MainAxisSize
    0.72
    CreateMap
    0.72
     パンチラ
    0.71
    <unused20>
    0.71
    <pad>
    0.70
    Act Density 0.051%

    No Known Activations