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

    Neuronpedia

    INDEX
    Explanations

    various instances of the word "Type" followed by numbers in a technical or programming context

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

    Type

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    horabuena
    -0.54
     wspania
    -0.49
     vuestra
    -0.45
     beider
    -0.44
     '\\;'
    -0.44
     gewisse
    -0.44
    UnsafeEnabled
    -0.43
    Ārējās
    -0.41
     Verständ
    -0.41
    esac
    -0.41
    POSITIVE LOGITS
     Type
    1.91
    Type
    1.37
     TYPE
    1.00
     Typ
    0.96
     Types
    0.89
     Tipo
    0.85
    Typ
    0.82
    TypeService
    0.79
    getType
    0.79
     setType
    0.78
    Act Density 0.006%

    No Known Activations