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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating relationships and connections among concepts

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

    prepositions followed by specific nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.50
     للمعارف
    -0.47
     oprot
    -0.47
    orith
    -0.45
     endforeach
    -0.45
    SharedCtor
    -0.44
    zoon
    -0.44
    InitVars
    -0.42
    ніципа
    -0.42
     malah
    -0.42
    POSITIVE LOGITS
     ſta
    0.50
    MessageTagHelper
    0.45
     ſtate
    0.42
    étoit
    0.42
     houſe
    0.40
     staden
    0.39
     autrefois
    0.39
     medlemmer
    0.39
    före
    0.38
     bénéficiaire
    0.38
    Act Density 0.614%

    No Known Activations