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

    Neuronpedia

    INDEX
    Explanations

    specific names or entities, particularly within mathematical or scientific contexts

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

    Romanian language and context markers

    np_acts-logits-general · gemini-2.0-flash

    Romanian names and academic contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     purpoſe
    -1.08
     picioare
    -1.06
     quæ
    -1.04
     houſe
    -1.01
     Diſ
    -0.98
     piele
    -0.98
     greateſt
    -0.98
     myſelf
    -0.97
     poffible
    -0.96
     ſtate
    -0.96
    POSITIVE LOGITS
     Romanian
    0.57
     Romania
    0.57
     useEffect
    0.54
    Romania
    0.52
     „
    0.50
     nr
    0.48
    „
    0.47
    EntityFramework
    0.46
    TypedDataSet
    0.45
     va
    0.45
    Act Density 0.051%

    No Known Activations