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

    Neuronpedia

    INDEX
    Explanations

    references to SQL statements and related programming constructs

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

    base following certain words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.52
     CanadaChoose
    -0.50
     TType
    -0.49
     tartalomajánló
    -0.48
     yyj
    -0.47
    ChildScrollView
    -0.47
     '{@
    -0.45
    Czytaj
    -0.45
    CppMethod
    -0.45
    WithIOException
    -0.45
    POSITIVE LOGITS
     base
    1.12
     bases
    0.87
    base
    0.85
    getBase
    0.82
    ibase
    0.81
     Base
    0.80
     based
    0.79
     BASE
    0.78
     basé
    0.75
    Base
    0.74
    Act Density 0.024%

    No Known Activations