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

    Neuronpedia

    INDEX
    Explanations

    terms related to double robustness in statistical methods

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

    double and doubling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mijne
    -0.54
     Inscrivez
    -0.53
     popoli
    -0.52
    /**
    -0.50
     zijne
    -0.48
     vermogen
    -0.48
     miei
    -0.44
     الرياضيه
    -0.43
     jurk
    -0.43
    genodigd
    -0.41
    POSITIVE LOGITS
     double
    1.55
     Double
    1.47
     DOUBLE
    1.41
    Double
    1.35
    double
    1.35
    DOUBLE
    1.23
     doble
    1.20
     triple
    1.05
     doubles
    1.05
     Doubles
    1.03
    Act Density 0.081%

    No Known Activations