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

    Neuronpedia

    INDEX
    Explanations

    punctuation and the structure of sentences or phrases

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

    and personal use

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bäst
    -0.36
     Kure
    -0.36
    esac
    -0.36
    staticmethod
    -0.35
     diante
    -0.33
     hjär
    -0.33
     Allo
    -0.32
    Schicken
    -0.32
    Allo
    -0.32
     remedi
    -0.32
    POSITIVE LOGITS
    WriteTagHelper
    0.61
    Tikang
    0.57
    neſs
    0.54
    WebElementEntity
    0.54
    setVerticalGroup
    0.50
    mergeFrom
    0.47
     propOrder
    0.47
     Wikimedijinoj
    0.45
     సౌకర్య
    0.44
     Purposes
    0.44
    Act Density 0.064%

    No Known Activations