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

    Neuronpedia

    INDEX
    Explanations

    export statements in code, particularly in JavaScript or TypeScript

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

    export declarations and their subsequent definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⓧ
    -0.47
     <<<<<<<<<<<<<<
    -0.43
     ✭✭
    -0.42
     transfieras
    -0.38
    indépendance
    -0.38
    了一眼
    -0.38
    ￡
    -0.37
     mourut
    -0.37
     cocina
    -0.36
    écoute
    -0.36
    POSITIVE LOGITS
     class
    0.70
    class
    0.54
     classes
    0.47
     getClass
    0.46
    signable
    0.44
    getClass
    0.44
     Klass
    0.43
    المكان
    0.43
    invokeLater
    0.42
     clase
    0.42
    Act Density 0.001%

    No Known Activations